© 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. 14127
    Prev
    Next
    INDEX
    Explanations

    instances where readers are asked to leave a comment

    oai_token-act-pair · gemini-2.0-flash

    comments

    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
    preventDefault
    -0.57
     déchir
    -0.54
     unfamiliar
    -0.54
     lautet
    -0.52
     dovre
    -0.51
     habituellement
    -0.51
    hithe
    -0.50
    cerpts
    -0.50
    stricken
    -0.50
    schnitt
    -0.48
    POSITIVE LOGITS
     CreateTagHelper
    0.82
    featureID
    0.73
    TintMode
    0.73
    ValueStyle
    0.68
    Personensuche
    0.66
     незавершена
    0.59
    DoubleQuotes
    0.57
    CodedInputStream
    0.56
     ErrIntOverflow
    0.55
    AccessorTable
    0.54
    Activations Density 0.294%

    No Known Activations