© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130219
    Prev
    Next
    INDEX
    Explanations

    Taliban, dinosaurs, bagels

    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_1_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
    y
    1.84
    و
    1.63
    u
    1.53
    <0x80>
    1.45
    il
    1.36
    et
    1.22
    ى
    1.18
    ↵
    1.13
    at
    1.09
    f
    1.06
    POSITIVE LOGITS
    \
    0.98
    は
    0.93
    お
    0.93
    AlignedText
    0.92
    ือ
    0.91
    ка
    0.89
     in
    0.88
    SleepHours
    0.87
    ها
    0.86
    したがって
    0.84
    Activations Density 0.001%

    No Known Activations