© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10233
    Prev
    Next
    INDEX
    Explanations

    square brackets, often within programming code or mathematical expressions

    oai_token-act-pair · gemini-2.0-flash

    brackets and structured data formats

    np_token-act-pair-logits · gpt-4o-mini

    Bracket

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Predecesor
    -0.69
    /*",
    -0.64
    ulongan
    -0.63
    mål
    -0.62
    ientôt
    -0.62
    ercises
    -0.62
    istoitu
    -0.61
    erba
    -0.60
    ]--;
    -0.60
    ätz
    -0.59
    POSITIVE LOGITS
     ddelweddau
    0.62
     itſelf
    0.59
     eorum
    0.57
     habet
    0.56
     poffible
    0.55
     againſt
    0.54
     orientale
    0.53
     Partager
    0.53
    “
    0.52
     ejus
    0.51
    Activations Density 1.904%

    No Known Activations