© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208189
    Prev
    Next
    INDEX
    Explanations

    restoring faces, breaking language, peaking levels

    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_25_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
    ası
    0.57
    uran
    0.56
    ha
    0.54
    add
    0.54
    asa
    0.52
    gek
    0.52
    go
    0.52
    翎
    0.52
    ato
    0.52
    aves
    0.52
    POSITIVE LOGITS
     unters
    0.46
     encaps
    0.46
    ной
    0.43
    卅
    0.43
     knih
    0.43
    いつ
    0.42
    平时
    0.42
    া
    0.41
    ้อง
    0.41
    心
    0.41
    Activations Density 0.000%

    No Known Activations