© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 242231
    Prev
    Next
    INDEX
    Explanations

    or until

    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_25_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
    精
    0.40
     데이터
    0.39
    肩
    0.38
     精
    0.37
     Scholars
    0.37
     Doctorate
    0.37
     Otros
    0.37
    掩
    0.37
     Att
    0.37
     Speakers
    0.36
    POSITIVE LOGITS
    enuh
    0.42
    purple
    0.42
     szabad
    0.42
    permission
    0.40
     laquelle
    0.40
    arki
    0.39
    angement
    0.39
    any
    0.39
    free
    0.39
    weird
    0.38
    Activations Density 0.000%

    No Known Activations