© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12839
    Prev
    Next
    INDEX
    Explanations

    instances of subjects "taking part" in studies or events

    oai_token-act-pair · gemini-2.0-flash

    part

    np_max-act-logits · gemini-2.0-flash

    take

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    AddHtmlAttribute
    -0.82
    ScopeManager
    -0.77
    出版年
    -0.71
    UseVisualStyle
    -0.71
    AsUp
    -0.68
    findpost
    -0.68
     ModelExpression
    -0.67
    Попис
    -0.67
     StatefulWidget
    -0.66
     AppCompat
    -0.63
    POSITIVE LOGITS
     part
    2.73
    part
    2.38
    Part
    2.11
     Part
    1.94
     parte
    1.85
     parts
    1.84
     PART
    1.70
    parts
    1.56
    PART
    1.53
     Teil
    1.45
    Activations Density 1.726%

    No Known Activations