© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14057
    Prev
    Next
    INDEX
    Explanations

    words and prepositions that often show up in narrative descriptions

    oai_token-act-pair · gemini-2.0-flash

    actions or travel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    المناصب
    -0.62
    +#+
    -0.60
    PerformLayout
    -0.58
     Administrativna
    -0.55
     betweenstory
    -0.54
    Życiorys
    -0.53
    ternut
    -0.50
    migrationBuilder
    -0.50
    énario
    -0.49
    Otherwise
    -0.48
    POSITIVE LOGITS
     hrab
    0.54
     inspires
    0.51
    mergeFrom
    0.48
     edif
    0.48
    untura
    0.47
     المكتبه
    0.47
    TAGE
    0.47
     ausz
    0.46
    __(/*!
    0.46
    ColumnHeaders
    0.46
    Activations Density 2.875%

    No Known Activations