© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11257
    Prev
    Next
    INDEX
    Explanations

    mentions of legal authority, court cases, and juridical language

    oai_token-act-pair · gemini-2.0-flash

    legal and gaming discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    مقاله
    -0.78
    principalColumn
    -0.75
    GeoNames
    -0.71
     Testamento
    -0.64
     ModelExpression
    -0.63
     MotionEvent
    -0.60
    下载附件
    -0.59
    
    -0.58
     Akismet
    -0.58
     bezeichneter
    -0.57
    POSITIVE LOGITS
     utafitiHapana
    0.75
     Roskov
    0.57
     ostavi
    0.52
     Administrativna
    0.51
    ्
    0.49
    intios
    0.48
     mergeFrom
    0.48
    ніципа
    0.48
    MigrationBuilder
    0.47
     cara
    0.47
    Activations Density 6.211%

    No Known Activations