© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 146720
    Prev
    Next
    INDEX
    Explanations

    list items

    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_18_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
    阃
    0.63
     uzav
    0.61
    nější
    0.59
     nový
    0.58
    łożyć
    0.55
     tři
    0.54
     роках
    0.54
     errichtet
    0.54
    CriteriaUtils
    0.54
     deň
    0.52
    POSITIVE LOGITS
     symmetric
    0.53
     syntactic
    0.53
    [
    0.53
    a
    0.52
     generic
    0.50
    (
    0.50
     the
    0.49
     syntax
    0.48
     sparse
    0.48
     rhythmic
    0.48
    Activations Density 0.000%

    No Known Activations