© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107864
    Prev
    Next
    INDEX
    Explanations

    language-specific suffixes

    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_1_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
    то
    1.58
    на
    1.49
    تي
    1.41
    ל
    1.38
    та
    1.37
    ש
    1.35
    ಮ
    1.32
    স
    1.30
    ↵↵
    1.26
    ك
    1.26
    POSITIVE LOGITS
     It
    1.29
     in
    1.16
    ,
    1.16
    :
    0.99
     I
    0.97
    摖
    0.93
    T
    0.92
    I
    0.92
    F
    0.91
    ling
    0.91
    Activations Density 0.002%

    No Known Activations