© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3471
    Prev
    Next
    INDEX
    Explanations

    text related to product releases and announcements.

    oai_token-act-pair · gemini-2.0-flash

    announcements and releases

    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
    IntoConstraints
    -0.95
     doInBackground
    -0.78
     RoutedEventArgs
    -0.77
    期刊论文
    -0.71
    TagMode
    -0.71
     NSCoder
    -0.69
    Архівовано
    -0.68
    enterOuterAlt
    -0.67
     kasarigan
    -0.66
     referenties
    -0.66
    POSITIVE LOGITS
     coming
    0.46
    utsal
    0.43
    public
    0.39
     Coming
    0.38
    reno
    0.38
    calendar
    0.37
     Fontana
    0.36
    杂
    0.36
    >>()
    0.36
     plans
    0.36
    Activations Density 0.780%

    No Known Activations