© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12456
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to graphs or figures in a scientific paper

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Roskov
    -0.65
    InputBorder
    -0.63
     Мексичка
    -0.62
     resourceCulture
    -0.61
    rusted
    -0.59
    =“
    -0.56
    Archived
    -0.56
    ArgsConstructor
    -0.55
     Italijanski
    -0.55
     autorytatywna
    -0.54
    POSITIVE LOGITS
    Figure
    0.89
     Figure
    0.84
    FIG
    0.79
     FIGURE
    0.77
    Fig
    0.77
     FIG
    0.74
     figure
    0.73
     Fig
    0.69
    fig
    0.68
    FIGURE
    0.67
    Activations Density 0.873%

    No Known Activations