© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25746
    Prev
    Next
    INDEX
    Explanations

    toggle visibility or state

    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_10_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
    a
    0.88
    es
    0.79
    ap
    0.69
    teilung
    0.68
    kta
    0.67
     from
    0.65
    h
    0.64
    k
    0.64
     phonons
    0.63
    dato
    0.63
    POSITIVE LOGITS
     jumpsuit
    0.66
    ри
    0.65
    ก็
    0.60
     eyep
    0.59
    സും
    0.54
     hyperlink
    0.54
     DMR
    0.54
    尓
    0.54
    IQUE
    0.53
     rind
    0.53
    Activations Density 0.001%

    No Known Activations