© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9365
    Prev
    Next
    INDEX
    Explanations

    technical counts and specifications related to hardware, code, and statistics

    oai_token-act-pair · gemini-2.0-flash

    scientific data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    interopRequire
    -0.76
     onBind
    -0.73
    MemoryWarning
    -0.63
    EnableWeb
    -0.62
    LookAnd
    -0.61
    ChildScrollView
    -0.60
    RuleContext
    -0.58
    Espèce
    -0.58
    forName
    -0.56
     שוליים
    -0.56
    POSITIVE LOGITS
    ционное
    0.49
    deres
    0.48
    новништво
    0.46
    Демографія
    0.46
     segreto
    0.45
    absolute
    0.44
     under
    0.44
     Unders
    0.42
    ゆき
    0.42
    ционного
    0.42
    Activations Density 3.750%

    No Known Activations