© 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. 9450
    Prev
    Next
    INDEX
    Explanations

    the action of listening

    oai_token-act-pair · gemini-2.0-flash

    instances of "listen" or listening

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

    listen

    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
    ніципа
    -0.62
    Listen
    -0.56
     Listen
    -0.52
     listen
    -0.51
     brz
    -0.44
    новниш
    -0.44
    urare
    -0.44
     List
    -0.44
    icordia
    -0.44
    PreferredItem
    -0.43
    POSITIVE LOGITS
     Exactos
    0.74
     closer
    0.73
    FormTagHelper
    0.72
    ViewFeatures
    0.66
     AspNetCore
    0.65
     to
    0.64
    AndEndTag
    0.63
     closely
    0.62
     Signalez
    0.61
    CloseOperation
    0.60
    Activations Density 1.197%

    No Known Activations