© 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-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 194502
    Prev
    Next
    INDEX
    Explanations

    Streamlit app

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (
    1.04
    ]
    0.93
    )
    0.88
     can
    0.85
     of
    0.80
    .
    0.76
    <0x0D>
    0.73
     at
    0.73
    ti
    0.71
     to
    0.69
    POSITIVE LOGITS
     PPAR
    0.71
     comenc
    0.68
     کاسینو
    0.66
     काफ़ी
    0.64
    럏
    0.64
     WENO
    0.64
     GraphQL
    0.63
     توانائی
    0.63
     JDBC
    0.63
    炵
    0.62
    Activations Density 0.001%

    No Known Activations