© 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. 5052
    Prev
    Next
    INDEX
    Explanations

    terms used in formal reports or studies

    oai_token-act-pair · gemini-2.0-flash

    arrangement

    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
    DoubleQuotes
    -0.85
     HasFactory
    -0.69
    FunctionFlags
    -0.65
     مرئيه
    -0.63
     ModelExpression
    -0.62
    ########.
    -0.62
    ArgsConstructor
    -0.60
     sacrifices
    -0.59
     things
    -0.57
     correlations
    -0.57
    POSITIVE LOGITS
     assignment
    0.71
     arrangement
    0.71
     opportunity
    0.67
     scheme
    0.66
     session
    0.65
     invitation
    0.61
     statement
    0.60
     épaules
    0.60
    opportunity
    0.59
     verdict
    0.59
    Activations Density 6.874%

    No Known Activations