© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12788
    Prev
    Next
    INDEX
    Explanations

    java documentation tags

    oai_token-act-pair · gemini-2.0-flash

    author

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    author
    -0.98
     author
    -0.95
     Author
    -0.84
    Author
    -0.80
    Authors
    -0.79
    authors
    -0.74
     autor
    -0.71
     authors
    -0.71
     AUTHOR
    -0.69
    AUTHOR
    -0.66
    POSITIVE LOGITS
    <bos>
    0.76
     Monfieur
    0.66
     Efq
    0.65
     ویکی‌پدیای
    0.60
     समीक्षाओं
    0.53
     Forumite
    0.51
     bezeichneter
    0.51
    eseorang
    0.50
     doubtnut
    0.50
    webElementXpaths
    0.49
    Activations Density 1.434%

    No Known Activations