© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 57780
    Prev
    Next
    INDEX
    Explanations

    suspend fun

    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
    Negative Logits
     It
    1.69
    ā
    1.45
    I
    1.40
     it
    1.34
    in
    1.29
    、
    1.29
     be
    1.19
    ized
    1.13
    و
    1.12
     There
    1.11
    POSITIVE LOGITS
    си
    1.41
     that
    1.34
     of
    1.28
    ード
    1.27
    ק
    1.23
    6
    1.22
    ס
    1.20
    ים
    1.20
    ب
    1.18
    ри
    1.16
    Activations Density 0.001%

    No Known Activations