© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15349
    Prev
    Next
    INDEX
    Explanations

    numerical data, including version numbers, ratings, and years

    oai_token-act-pair · gemini-2.0-flash

    numerical data/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
    Referencies
    -0.52
    AppData
    -0.43
     lagoons
    -0.43
    migrationBuilder
    -0.42
     незавершена
    -0.42
    rrggbb
    -0.42
    AndEndTag
    -0.42
    Cubit
    -0.42
     αν
    -0.41
     sanitaire
    -0.41
    POSITIVE LOGITS
     Paglinawan
    0.75
     بيها
    0.69
    Adapters
    0.62
    SourceChecksum
    0.58
    verständlich
    0.55
    andafter
    0.54
    verwijspagina
    0.54
    исленность
    0.54
     "..\..\
    0.53
     calendriers
    0.53
    Activations Density 4.782%

    No Known Activations