© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14824
    Prev
    Next
    INDEX
    Explanations

    variety shows

    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_13_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
    셰
    0.37
    le
    0.32
     presente
    0.31
    埙
    0.31
    ge
    0.31
     V
    0.28
    те
    0.28
     baj
    0.28
     čern
    0.28
     fu
    0.28
    POSITIVE LOGITS
    .(\
    0.33
     Бекер
    0.32
    底
    0.32
     Боли
    0.31
    तीच्या
    0.31
     Landry
    0.30
    ."[
    0.29
     वस्तू
    0.29
     कारण
    0.29
     त्यांच्या
    0.29
    Activations Density 0.008%

    No Known Activations