© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 41095
    Prev
    Next
    INDEX
    Explanations

    don't skimp on

    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_11_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
    man
    0.72
    ES
    0.61
    õ
    0.60
    č
    0.59
    人力
    0.57
    想起
    0.57
    у
    0.56
    manual
    0.55
    々
    0.55
    ed
    0.55
    POSITIVE LOGITS
     Endocrinology
    0.63
     ovation
    0.61
     lipos
    0.58
     Their
    0.57
    ”،
    0.57
     endocr
    0.57
    Са
    0.56
     Logitech
    0.56
     nineties
    0.56
     propriétés
    0.55
    Activations Density 0.001%

    No Known Activations