© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123913
    Prev
    Next
    INDEX
    Explanations

    make sure to

    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
    ли
    0.83
     an
    0.80
    ö
    0.80
    լ
    0.73
    ení
    0.73
    ↵
    0.72
     clos
    0.72
    т
    0.71
    ian
    0.71
     to
    0.70
    POSITIVE LOGITS
    且
    0.75
    К
    0.74
    5
    0.64
    Ꮇ
    0.64
    asts
    0.63
    ad
    0.63
    Фе
    0.63
    assured
    0.61
    a
    0.61
    macro
    0.60
    Activations Density 0.001%

    No Known Activations