© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8126
    Prev
    Next
    INDEX
    Explanations

    a variety of words that could belong to different unrelated topics

    oai_token-act-pair · gemini-2.0-flash

    time frequency

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     /\.
    -0.60
    oredCriteria
    -0.51
     VIDEOTAPE
    -0.51
    extAlignment
    -0.51
    iej
    -0.50
    TypedDataSet
    -0.50
     transfieras
    -0.49
    页面存档备份
    -0.49
     Sulphur
    -0.48
    muerzo
    -0.47
    POSITIVE LOGITS
     daily
    2.13
    daily
    1.74
     weekly
    1.67
     everyday
    1.57
     DAILY
    1.53
    Daily
    1.52
     annually
    1.52
     Daily
    1.47
     monthly
    1.46
     yearly
    1.43
    Activations Density 2.066%

    No Known Activations