© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2700
    Prev
    Next
    INDEX
    Explanations

    names of people, especially scientists and attorneys, often within citations or legal contexts

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    '
    -0.54
    Erreferentziak
    -0.49
    ’
    -0.46
     individuale
    -0.42
     destra
    -0.41
    vdots
    -0.41
    iterable
    -0.40
    contentLoaded
    -0.40
     Polak
    -0.40
    vų
    -0.40
    POSITIVE LOGITS
    __((
    0.77
     pettico
    0.77
     onOptions
    0.73
    tvguidetime
    0.69
    ríamos
    0.69
     للاسماء
    0.68
     GenerationType
    0.67
    CreateModel
    0.67
    новниш
    0.66
    HomeAsUp
    0.66
    Activations Density 2.644%

    No Known Activations