© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9165
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns in active declarative statements

    oai_token-act-pair · gemini-2.0-flash

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     mám
    -0.42
    고
    -0.39
    änglich
    -0.38
    oxo
    -0.37
    ţă
    -0.37
     speak
    -0.37
    SWR
    -0.37
     хочу
    -0.36
    zipCode
    -0.36
    yorum
    -0.35
    POSITIVE LOGITS
     resourceCulture
    0.97
    AccessorTable
    0.89
    ReusableCell
    0.86
     ModelExpression
    0.84
     poveznice
    0.83
    elemField
    0.80
    UseVisualStyle
    0.79
    migrationBuilder
    0.77
    EDEFAULT
    0.77
    XMLSchema
    0.76
    Activations Density 0.430%

    No Known Activations