© 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. 8473
    Prev
    Next
    INDEX
    Explanations

    hyphenated page number ranges

    oai_token-act-pair · gemini-2.0-flash

    academic publications

    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
    rrggbb
    -0.51
    ActivityResult
    -0.50
    EntityFramework
    -0.48
    IntoConstraints
    -0.44
    inh
    -0.42
     due
    -0.41
    пь
    -0.41
    NoError
    -0.41
    Населення
    -0.40
    ViewById
    -0.40
    POSITIVE LOGITS
     विश्वसनीयता
    0.83
     समीक्षक
    0.73
    #+#
    0.63
     uſe
    0.61
    ThroughAttribute
    0.61
    Rüyada
    0.59
     ModelExpression
    0.59
    roek
    0.58
     beſt
    0.58
     reaſon
    0.57
    Activations Density 0.143%

    No Known Activations