© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12843
    Prev
    Next
    INDEX
    Explanations

    references to legal documents or citations

    oai_token-act-pair · gemini-2.0-flash

    iting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     MainAxisSize
    -0.85
     الحره
    -0.85
     $_"
    -0.80
     '\\;'
    -0.77
     дописавши
    -0.77
     poffible
    -0.76
    UnsafeEnabled
    -0.76
    RectangleBorder
    -0.75
    CardContent
    -0.74
     صوتيه
    -0.73
    POSITIVE LOGITS
    migrationBuilder
    0.40
    斎藤
    0.40
    ...
    0.38
     situation
    0.38
    bentukan
    0.37
    Compose
    0.36
    via
    0.36
    pau
    0.36
     Guimarães
    0.35
    Exodus
    0.34
    Activations Density 3.985%

    No Known Activations