© 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. 125217
    Prev
    Next
    INDEX
    Explanations

    long tail

    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
     have
    0.80
    ،
    0.78
    c
    0.70
    have
    0.63
    groom
    0.62
    travel
    0.61
    T
    0.61
    work
    0.61
     are
    0.60
    agers
    0.60
    POSITIVE LOGITS
    ни
    0.91
    ない
    0.86
    ри
    0.84
    ー
    0.83
    ני
    0.78
    ン
    0.70
    は
    0.68
    는
    0.67
    נה
    0.67
    ยัง
    0.67
    Activations Density 0.001%

    No Known Activations