© 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. 159490
    Prev
    Next
    INDEX
    Explanations

    string manipulation functions

    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
    ла
    1.56
    '
    1.47
    "
    1.45
    า
    1.41
    ри
    1.38
    리
    1.33
    та
    1.25
    ำ
    1.22
    /
    1.09
    ;
    1.09
    POSITIVE LOGITS
    s
    1.17
    over
    1.08
    ைட்
    1.06
     distribu
    0.95
     necessario
    0.92
     repel
    0.90
     diminu
    0.88
    ind
    0.88
     rappel
    0.86
     somet
    0.85
    Activations Density 0.003%

    No Known Activations