© 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. 124286
    Prev
    Next
    INDEX
    Explanations

    rare species

    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
    ير
    0.79
    น
    0.77
    ות
    0.76
     rares
    0.74
    ↵↵
    0.74
     എന്നാൽ
    0.72
    uée
    0.71
    ン
    0.70
     แต่
    0.69
    н
    0.69
    POSITIVE LOGITS
    t
    0.67
    don
    0.66
    for
    0.64
    r
    0.62
    des
    0.62
    true
    0.61
    gent
    0.61
    ssä
    0.61
    dbh
    0.61
    kafka
    0.61
    Activations Density 0.000%

    No Known Activations