© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11722
    Prev
    Next
    INDEX
    Explanations

    words and phrases in a mix of languages related to gambling, especially online slot machines, and possibly including some proper names

    oai_token-act-pair · gemini-2.0-flash

    Code/Spanish/Portuguese

    np_max-act-logits · gemini-2.0-flash

    Spanish/Portuguese words

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -0.52
     &___
    -0.49
     IBOutlet
    -0.49
     CreateTagHelper
    -0.48
    TemporalType
    -0.47
    htub
    -0.45
     كومونز
    -0.44
    :✨
    -0.44
    CommandText
    -0.44
     properties
    -0.43
    POSITIVE LOGITS
    AnchorStyles
    0.69
     cherchés
    0.63
    IsMutable
    0.60
     Disagree
    0.56
     religieuse
    0.55
    RenderAtEndOf
    0.54
    󠁢
    0.53
     mu
    0.52
     clearColor
    0.52
     Myself
    0.50
    Activations Density 1.287%

    No Known Activations