© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87004
    Prev
    Next
    INDEX
    Explanations

    early warning systems

    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_3_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
    و
    1.07
    ھی
    0.75
    ו
    0.75
    ומי
    0.73
    ان
    0.71
    ன
    0.70
    ِی
    0.70
    다
    0.69
     दट
    0.66
     informacje
    0.65
    POSITIVE LOGITS
    r
    1.02
    is
    0.96
    -
    0.73
    b
    0.72
     is
    0.71
    ok
    0.71
    on
    0.70
    f
    0.68
    );
    0.65
     from
    0.64
    Activations Density 0.002%

    No Known Activations