© 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. 4876
    Prev
    Next
    INDEX
    Explanations

    words involved in making requests

    oai_token-act-pair · gemini-2.0-flash

    requests

    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
    Not in Any Lists

    No Comments

    Negative Logits
     насељу
    -0.63
    enumi
    -0.60
    RegistryLite
    -0.60
     Pingback
    -0.60
     FetchType
    -0.58
     OTO
    -0.57
    тет
    -0.55
    arakhand
    -0.54
    Чыганаклар
    -0.54
    ResumeLayout
    -0.52
    POSITIVE LOGITS
    ivamente
    0.52
     please
    0.50
    ########.
    0.49
     everyone
    0.47
    帖最后由
    0.46
     woe
    0.45
     कृपया
    0.44
     }}$}
    0.43
    Everyone
    0.43
     Vikipedi
    0.43
    Activations Density 0.764%

    No Known Activations