© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 135447
    Prev
    Next
    INDEX
    Explanations

    codec ranking

    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
    Negative Logits
    ו
    1.27
    基づ
    1.06
    д
    1.06
     rozwo
    1.05
    ं
    1.05
    و
    1.05
     peligro
    1.04
     comenc
    1.04
    د
    1.04
    ó
    1.04
    POSITIVE LOGITS
     are
    1.70
     as
    1.52
     to
    1.48
    ية
    1.28
     at
    1.20
    are
    1.17
    to
    1.16
    bs
    1.05
    1.01
    s
    1.01
    Activations Density 0.000%

    No Known Activations