© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14150
    Prev
    Next
    INDEX
    Explanations

    data from a debug log, with a focus on file paths and network configuration

    oai_token-act-pair · gemini-2.0-flash

    code or paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Thursday
    -0.81
     Thursdays
    -0.76
    Thursday
    -0.75
     jeudi
    -0.74
     thursday
    -0.70
     Donnerstag
    -0.68
     THURSDAY
    -0.65
    Thurs
    -0.65
     Fourteenth
    -0.64
     Thurs
    -0.64
    POSITIVE LOGITS
     Tuchel
    0.64
     Lenin
    0.64
     Capitan
    0.63
    gonic
    0.59
     cheese
    0.59
    RegressionTest
    0.58
     ITA
    0.57
     Neer
    0.57
    gery
    0.57
     yPos
    0.57
    Activations Density 8.145%

    No Known Activations