© 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. 34790
    Prev
    Next
    INDEX
    Explanations

    where the emphasis is

    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
    0.88
    ore
    0.83
    u
    0.82
    ib
    0.78
    h
    0.71
    aps
    0.69
    elt
    0.67
    ur
    0.66
    a
    0.64
    uhe
    0.63
    POSITIVE LOGITS
    т
    1.09
    ви
    0.97
    나
    0.89
    ర
    0.85
    어
    0.81
    يد
    0.81
    ら
    0.80
    रा
    0.79
    오
    0.79
    з
    0.79
    Activations Density 0.009%

    No Known Activations