© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111576
    Prev
    Next
    INDEX
    Explanations

    skiing

    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_2_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
    i
    1.21
    kannya
    1.06
    u
    1.06
    z
    1.03
    ﻦ
    0.97
    b
    0.96
    konto
    0.95
    kker
    0.93
    zilla
    0.92
     ولوبی
    0.92
    POSITIVE LOGITS
    ع
    1.67
    ح
    1.63
    ار
    1.55
    是
    1.38
    أ
    1.32
    لا
    1.28
    고
    1.26
    人
    1.25
    1
    1.13
    ли
    1.13
    Activations Density 0.000%

    No Known Activations