© 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. 13712
    Prev
    Next
    INDEX
    Explanations

    the word "the" preceded by certain prepositions or conjunctions

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash

    technical terminology or identifiers

    np_token-act-pair-logits · gpt-4o-mini
    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
     figure
    -0.71
     figures
    -0.64
     Ex
    -0.64
     figura
    -0.63
    figures
    -0.62
    figure
    -0.58
     ex
    -0.57
    ex
    -0.57
    Ex
    -0.56
    figs
    -0.50
    POSITIVE LOGITS
     ProtoMessage
    0.89
    WithIOException
    0.86
    HtmlAttribute
    0.82
    DockStyle
    0.76
    adpleegd
    0.69
     Roskov
    0.69
    expandindo
    0.69
    WireFormatLite
    0.69
    Билгалдахарш
    0.68
    CppMethod
    0.65
    Activations Density 0.496%

    No Known Activations