© 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. 2108
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and symbols

    oai_token-act-pair · gemini-2.0-flash

    non-English words or terminologies

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

    mathematical/scientific equations

    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
    richTextPanel
    -0.77
    GOTREF
    -0.75
     AssemblyCulture
    -0.70
     autorytatywna
    -0.69
    RTLR
    -0.65
    Portail
    -0.60
    )}^{
    -0.60
     snippetHide
    -0.59
    RTEE
    -0.56
     ویکی‌پدیا
    -0.56
    POSITIVE LOGITS
    afy
    0.48
    lső
    0.46
    didReceive
    0.46
     repente
    0.44
     وز
    0.44
     turbin
    0.44
     useAuth
    0.41
    ukone
    0.41
    īgā
    0.41
    ndham
    0.41
    Activations Density 9.924%

    No Known Activations