© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30488
    Prev
    Next
    INDEX
    Explanations

    variable names

    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_31_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
     commenced
    0.44
     Küh
    0.41
     OK
    0.36
     Zub
    0.36
    髡
    0.36
    ivan
    0.35
    めん
    0.35
    稃
    0.35
     Walton
    0.34
     Kanji
    0.34
    POSITIVE LOGITS
    logging
    0.38
     हरिद्वार
    0.38
    udur
    0.36
    birth
    0.35
     parâmetros
    0.35
    Segue
    0.34
     ไง
    0.34
     representa
    0.34
     आमंत्रित
    0.33
     decembrie
    0.33
    Activations Density 0.000%

    No Known Activations