© 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. 41643
    Prev
    Next
    INDEX
    Explanations

    Russian/Slavic, French, German, Chinese characters

    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
    u
    0.88
    y
    0.82
    r
    0.82
    t
    0.74
    cemia
    0.71
    I
    0.69
     I
    0.68
    세요
    0.66
    stripe
    0.66
    하는
    0.66
    POSITIVE LOGITS
    ة
    0.94
    ка
    0.85
    ك
    0.83
    '
    0.75
    м
    0.71
    م
    0.71
    的
    0.71
    are
    0.70
    (
    0.69
                    
    0.69
    Activations Density 0.002%

    No Known Activations