© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132851
    Prev
    Next
    INDEX
    Explanations

    Russian prefixes and 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_6_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
    ны
    1.16
    ilibre
    1.00
    +","+
    0.97
    يرا
    0.94
    iende
    0.93
    ку
    0.92
    льним
    0.91
    скага
    0.90
    يز
    0.89
    ルフ
    0.87
    POSITIVE LOGITS
     an
    1.36
    л
    1.30
    F
    1.30
    B
    1.29
    X
    1.27
    K
    1.27
    W
    1.26
     that
    1.25
    V
    1.24
    त
    1.23
    Activations Density 0.000%

    No Known Activations