© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159430
    Prev
    Next
    INDEX
    Explanations

    ht followed by common Russian word endings

    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
    L
    1.48
    B
    1.37
    ۔
    1.32
    V
    1.25
    ।
    1.21
    R
    1.19
    uk
    1.17
    P
    1.17
    K
    1.17
    G
    1.16
    POSITIVE LOGITS
     a
    1.26
    ,
    1.19
    pesar
    1.00
    стта
    1.00
    ۹
    0.97
     sự
    0.96
     quá
    0.95
     существенно
    0.94
    ವ್
    0.93
    ↵
    0.92
    Activations Density 0.000%

    No Known Activations