© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91178
    Prev
    Next
    INDEX
    Explanations

    Polish and Russian grammar

    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_3_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
    an
    1.16
    a
    1.15
    ه
    0.87
     that
    0.80
    9
    0.80
    া
    0.79
    i
    0.75
    board
    0.72
     que
    0.70
    very
    0.69
    POSITIVE LOGITS
     ایرانی
    0.81
    ل
    0.78
    тли
    0.74
    ેટ
    0.73
    蟀
    0.73
     інші
    0.71
     injunctive
    0.70
    姮
    0.70
    acariy
    0.70
     aflat
    0.69
    Activations Density 0.004%

    No Known Activations