© 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. 241864
    Prev
    Next
    INDEX
    Explanations

    I, my, we

    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
    Not in Any Lists

    No Comments

    Negative Logits
     transmission
    0.36
     string
    0.35
     kne
    0.35
    elesaian
    0.34
    argent
    0.34
     front
    0.34
     national
    0.34
     "
    0.33
     enfin
    0.33
     penit
    0.33
    POSITIVE LOGITS
     ماما
    0.48
    មើល
    0.43
    চ্ছা
    0.41
     இதுவரை
    0.39
    phalodes
    0.38
    あす楽
    0.38
    THAN
    0.38
     باور
    0.38
    冭
    0.38
    IDTH
    0.37
    Activations Density 0.000%

    No Known Activations