© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12787
    Prev
    Next
    INDEX
    Explanations

    the word "title" outside of code blocks.

    oai_token-act-pair · gemini-2.0-flash

    title

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Privacidade
    -0.60
    resents
    -0.57
    führt
    -0.56
    complexContent
    -0.54
    jectures
    -0.53
    rind
    -0.51
    namon
    -0.50
     svolta
    -0.50
    alite
    -0.50
     незавершена
    -0.49
    POSITIVE LOGITS
    లాలు
    0.62
    BeginContext
    0.56
    PreferredItem
    0.55
    AddTagHelper
    0.54
    CodeAttribute
    0.54
    Kjelder
    0.52
     الرياضيه
    0.52
    WireFormatLite
    0.51
    mergeFrom
    0.51
    !*\
    0.51
    Activations Density 5.762%

    No Known Activations