© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5823
    Prev
    Next
    INDEX
    Explanations

    text about using kitchen tools

    oai_token-act-pair · gemini-2.0-flash

    varied text and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Gaston
    -0.50
     produt
    -0.47
     acceptez
    -0.45
    mintaan
    -0.44
     odb
    -0.43
    BoxShadow
    -0.43
    귀
    -0.43
     económicas
    -0.42
    findpost
    -0.42
     promo
    -0.42
    POSITIVE LOGITS
     سكانية
    0.76
     grate
    0.68
    PhysRev
    0.67
     mixers
    0.67
     lenker
    0.66
     mixes
    0.66
    esModule
    0.63
     الرياضيه
    0.62
    migrationBuilder
    0.61
    تفصیلات
    0.60
    Activations Density 2.485%

    No Known Activations