© 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. 103418
    Prev
    Next
    INDEX
    Explanations

    k followed by punctuation or common words

    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
    0
    1.55
    '
    1.39
    et
    1.16
    !
    1.11
    \
    1.06
    2
    1.05
    ll
    0.99
    ä
    0.95
    ko
    0.95
    0.95
    POSITIVE LOGITS
    ين
    1.25
    из
    1.18
     commande
    1.14
     буль
    1.14
     entice
    1.13
     می‌دهد
    1.13
     térm
    1.12
     costitu
    1.10
     cataract
    1.09
     derece
    1.09
    Activations Density 0.001%

    No Known Activations