© 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. 88646
    Prev
    Next
    INDEX
    Explanations

    small, night, simple

    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
    Negative Logits
    ment
    0.53
    تها
    0.49
    تك
    0.46
    ö
    0.46
    腸
    0.46
    肠
    0.45
    стта
    0.44
     훨씬
    0.44
    കൾ
    0.44
    เข้าไป
    0.44
    POSITIVE LOGITS
     サイ
    0.58
    この
    0.57
     будь
    0.57
    癀
    0.57
    this
    0.56
     Новый
    0.56
    Any
    0.55
    AudioFocus
    0.55
     این
    0.55
    GES
    0.55
    Activations Density 0.037%

    No Known Activations