© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14979
    Prev
    Next
    INDEX
    Explanations

    uses of words like "this" in the context of a discussion

    oai_token-act-pair · gemini-2.0-flash

    references to articles or specific topics

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

    this

    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
     I
    -0.52
    me
    -0.46
     No
    -0.44
     me
    -0.44
     в
    -0.44
    at
    -0.43
     in
    -0.42
    daj
    -0.42
    (
    -0.42
    No
    -0.42
    POSITIVE LOGITS
    expandindo
    1.02
     itſelf
    0.96
     BoxFit
    0.96
     InputDecoration
    0.90
    Билгалдахарш
    0.88
    ValueStyle
    0.86
    aarrggbb
    0.86
    yntaxException
    0.85
    =$?
    0.84
     Мексичка
    0.82
    Activations Density 0.782%

    No Known Activations