© 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. 108541
    Prev
    Next
    INDEX
    Explanations

    Russian grammatical cases

    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
    ,
    0.83
     you
    0.80
     тобі
    0.78
    و
    0.74
    ו
    0.74
    ttino
    0.71
     (~
    0.70
     autochtones
    0.69
     erhe
    0.68
     limbo
    0.67
    POSITIVE LOGITS
    of
    1.33
    and
    1.16
    3
    1.09
    it
    1.05
    に
    0.98
    માં
    0.95
    ב
    0.94
    ä
    0.93
    は
    0.88
    ่า
    0.86
    Activations Density 0.001%

    No Known Activations