© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198076
    Prev
    Next
    INDEX
    Explanations

    looking at one's reflection

    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_12_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
     SPC
    0.60
    ㎎
    0.56
    ㎠
    0.56
     SPMs
    0.54
    isko
    0.54
    DanhMucSP
    0.54
    sendKeyDown
    0.52
     Suz
    0.51
    蛔
    0.51
     CGRectMake
    0.50
    POSITIVE LOGITS
    ôté
    0.52
    response
    0.49
     colectivo
    0.46
    тите
    0.45
     বাড়ি
    0.44
    หน้าที่
    0.44
    obs
    0.44
    ologische
    0.43
    йної
    0.43
     tiring
    0.43
    Activations Density 0.002%

    No Known Activations