© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59368
    Prev
    Next
    INDEX
    Explanations

    VStack, HStack, LazyVStack, LazyVGrid, List

    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
    い
    1.11
    ัน
    0.96
    ί
    0.95
    ILL
    0.95
    含ま
    0.95
    ier
    0.91
    ור
    0.91
    ุ
    0.91
    AL
    0.89
    ре
    0.88
    POSITIVE LOGITS
    s
    1.30
    a
    1.30
    ت
    1.25
    一
    1.09
    一系列
    0.99
    t
    0.97
    ség
    0.96
    i
    0.95
    ς
    0.95
    습니다
    0.94
    Activations Density 0.005%

    No Known Activations