© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9603
    Prev
    Next
    INDEX
    Explanations

    references to musical artists, bands, and related terms

    oai_token-act-pair · gemini-2.0-flash

    band

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     band
    -2.78
     Band
    -2.53
    Band
    -2.50
    band
    -2.42
     bands
    -2.39
     BAND
    -2.34
    BAND
    -2.28
     Bands
    -2.19
    bands
    -2.11
    Bands
    -1.91
    POSITIVE LOGITS
    ագրություններ
    0.66
     capilar
    0.53
     Lithuan
    0.52
    SharedDtor
    0.51
     Ruhm
    0.51
    égias
    0.50
     ppb
    0.50
     كومونز
    0.49
     itſelf
    0.47
     Russland
    0.47
    Activations Density 5.830%

    No Known Activations