© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 88348
    Prev
    Next
    INDEX
    Explanations

    Russian language

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    ت
    0.71
    ل
    0.69
    т
    0.64
    л
    0.57
    त
    0.52
    ל
    0.52
    F
    0.50
    N
    0.50
    L
    0.50
    G
    0.48
    POSITIVE LOGITS
    稞
    0.43
     appreciably
    0.42
     monks
    0.41
     Marne
    0.41
    িলম্বে
    0.41
    localVarHTTP
    0.40
     biocompat
    0.40
     হোমিওপ্যাথিক
    0.40
     একথা
    0.40
     heterozygous
    0.39
    Activations Density 0.000%

    No Known Activations