© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132986
    Prev
    Next
    INDEX
    Explanations

    word document

    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_6_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
    d
    1.24
    b
    1.23
    m
    1.02
    as
    1.01
    c
    1.00
    t
    0.98
    in
    0.96
    ت
    0.95
    et
    0.94
    ات
    0.94
    POSITIVE LOGITS
    ä
    1.02
    arı
    0.96
    ă
    0.96
     escrito
    0.94
     designado
    0.93
    ý
    0.88
     an
    0.87
    ?
    0.86
    ü
    0.86
     sufrir
    0.85
    Activations Density 0.000%

    No Known Activations