© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3431
    Prev
    Next
    INDEX
    Explanations

    short words that often come before nouns, such as "in", "of", "the", "his", "to", "from", and "by"

    oai_token-act-pair · gemini-2.0-flash

    references to identity and cultural discussion

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    出版年
    -0.59
    ItemBackground
    -0.58
     ModelExpression
    -0.56
     eccell
    -0.55
    muerzo
    -0.54
     intStringLen
    -0.50
     jspb
    -0.50
    GraphicsUnit
    -0.50
    awtextra
    -0.49
     nadzie
    -0.48
    POSITIVE LOGITS
     drive
    0.56
     Drive
    0.53
    drive
    0.53
    Referanser
    0.53
    KEYCODE
    0.52
    matchCondition
    0.51
    ondale
    0.50
    archiviato
    0.49
     comment
    0.48
     Cho
    0.48
    Activations Density 0.545%

    No Known Activations