© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10400
    Prev
    Next
    INDEX
    Explanations

    lines beginning with "http" or "https" followed by other words

    oai_token-act-pair · gemini-2.0-flash

    links and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    PerformLayout
    -0.84
    GEBURTSDATUM
    -0.77
     mergeFrom
    -0.73
    RenderAtEndOf
    -0.70
     >=",
    -0.70
    UnusedPrivate
    -0.66
    IComponent
    -0.63
    RTLD
    -0.62
    ResumeLayout
    -0.62
    Nationalité
    -0.61
    POSITIVE LOGITS
    /
    0.77
    Risultati
    0.53
     متعلقه
    0.52
    Искәрмәләр
    0.49
    тельств
    0.48
     Cæsar
    0.47
    primaryColor
    0.46
    yarnpkg
    0.46
     فريبيس
    0.46
    twimg
    0.45
    Activations Density 4.204%

    No Known Activations