© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192839
    Prev
    Next
    INDEX
    Explanations

    come in

    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_4_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
    ка
    1.52
    ك
    1.41
    к
    1.12
    ية
    1.09
     في
    1.00
    ০০
    0.98
    كيت
    0.98
     в
    0.88
    га
    0.88
     in
    0.87
    POSITIVE LOGITS
    t
    1.19
    ون
    1.01
    tl
    0.95
    tis
    0.95
    다른
    0.93
    tt
    0.90
    श
    0.90
     \
    0.90
    -
    0.89
    ب
    0.89
    Activations Density 0.009%

    No Known Activations