© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5048
    Prev
    Next
    INDEX
    Explanations

    a mix of programming code, legalese, references to organizations, and a few conversational elements.

    oai_token-act-pair · gemini-2.0-flash

    Code/algorithms/random text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     الحره
    -0.98
    MigrationBuilder
    -0.97
     بيها
    -0.95
    ंदीखरीदारी
    -0.93
    FunctionFlags
    -0.88
    FormTagHelper
    -0.87
    AndEndTag
    -0.87
    migrationBuilder
    -0.87
    IGraphics
    -0.85
     للمعارف
    -0.81
    POSITIVE LOGITS
    Παραπομπές
    0.40
     pure
    0.38
     Pure
    0.37
    pure
    0.37
     Another
    0.37
    seur
    0.37
    zeich
    0.36
    Another
    0.36
     szint
    0.36
    ↵↵
    0.35
    Activations Density 14.262%

    No Known Activations