© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15308
    Prev
    Next
    INDEX
    Explanations

    hotel restaurant pub

    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
    Negative Logits
    ли
    0.64
     известен
    0.55
    <sup>
    0.54
    كيت
    0.53
     К
    0.53
     divided
    0.52
     descrito
    0.52
    </strong>
    0.52
     к
    0.52
     أ
    0.51
    POSITIVE LOGITS
    ODO
    0.64
    Ammo
    0.63
    yyam
    0.58
     pedicure
    0.57
    कं
    0.53
    Cic
    0.52
     sog
    0.50
    Ejercicio
    0.50
    EEG
    0.50
    Skeleton
    0.50
    Activations Density 0.000%

    No Known Activations