© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6036
    Prev
    Next
    INDEX
    Explanations

    a variety of contexts including probability calculations, relative temporal position, amount, and physical location.

    oai_token-act-pair · gemini-2.0-flash

    mixed contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     few
    -1.59
    few
    -1.49
     Few
    -1.42
    Few
    -1.40
     quelques
    -1.38
     three
    -1.30
     FEW
    -1.29
     five
    -1.27
     four
    -1.24
     two
    -1.20
    POSITIVE LOGITS
     للاسماء
    0.62
    MigrationBuilder
    0.58
    etCode
    0.58
    principalColumn
    0.56
     dieux
    0.52
     InputDecoration
    0.52
    giène
    0.51
    AsUp
    0.51
    findpost
    0.50
     peuples
    0.48
    Activations Density 2.847%

    No Known Activations