© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136826
    Prev
    Next
    INDEX
    Explanations

    rollers and lithography

    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_12_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
     curls
    0.60
    ਦਰ
    0.55
     wigs
    0.55
     দুটি
    0.54
    attoos
    0.54
    ﻥ
    0.54
     cheveux
    0.54
     necklaces
    0.53
    🌝
    0.53
     capelli
    0.52
    POSITIVE LOGITS
    s
    0.68
    v
    0.65
    Fleet
    0.50
    ifton
    0.50
    S
    0.50
     транспорт
    0.47
     v
    0.47
    *
    0.47
     service
    0.46
    [
    0.46
    Activations Density 0.004%

    No Known Activations