© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4916
    Prev
    Next
    INDEX
    Explanations

    text related to radio broadcasting, especially music broadcasting by specific DJs and recording companies

    oai_token-act-pair · gemini-2.0-flash

    music

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    脚注の使い方
    -0.69
    出版年
    -0.67
     Audiodateien
    -0.65
     AspNetCore
    -0.63
     Drapeau
    -0.60
    ruptedException
    -0.56
     незавершена
    -0.55
    </caption>
    -0.55
    WriteTagHelper
    -0.54
     rendering
    -0.52
    POSITIVE LOGITS
    setLayoutManager
    0.51
     opérés
    0.49
    groupby
    0.47
    Cyfeiriadau
    0.47
    nloa
    0.46
     ?>/
    0.46
    PathVariable
    0.45
     TRABAJO
    0.45
    StreetMap
    0.44
    razos
    0.43
    Activations Density 0.876%

    No Known Activations