© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48254
    Prev
    Next
    INDEX
    Explanations

    Add

    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_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     TRUST
    0.41
    Posture
    0.38
    戤
    0.38
     furnished
    0.37
    र्नर
    0.37
    neyland
    0.37
    onuclear
    0.36
    櫚
    0.36
     trusts
    0.36
    AMSUNG
    0.36
    POSITIVE LOGITS
     означает
    0.37
     signif
    0.35
     signifie
    0.34
     significa
    0.34
    感
    0.33
    ၚ
    0.33
     anunciou
    0.33
     implies
    0.33
     promete
    0.33
    implies
    0.32
    Activations Density 0.011%

    No Known Activations