© 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. 13511
    Prev
    Next
    INDEX
    Explanations

    responses or comments.

    oai_token-act-pair · gemini-2.0-flash

    forum posts

    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
    SourceChecksum
    -0.81
    migrationBuilder
    -0.70
    EDEFAULT
    -0.64
    Tikang
    -0.63
    MigrationBuilder
    -0.63
    MathML
    -0.63
    NameInMap
    -0.61
    RTLR
    -0.60
    styleType
    -0.60
    jooq
    -0.59
    POSITIVE LOGITS
    vatten
    0.49
    cetype
    0.47
    idosis
    0.47
    ymce
    0.47
     Ather
    0.46
    вгения
    0.46
    argb
    0.46
    Feed
    0.46
    UTES
    0.46
    InstrumentedTest
    0.45
    Activations Density 0.581%

    No Known Activations