© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46505
    Prev
    Next
    INDEX
    Explanations

    find item by id

    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_22_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
     para
    0.49
    stru
    0.46
    4
    0.45
    up
    0.43
    ische
    0.42
     Para
    0.41
    para
    0.41
    aff
    0.41
    isf
    0.40
    un
    0.40
    POSITIVE LOGITS
     tanned
    0.48
    воен
    0.48
     Tatha
    0.46
    茉
    0.46
     recip
    0.46
     ಸಂಖ್ಯ
    0.44
     ~(~)
    0.44
     sekarang
    0.44
    ㄑ
    0.44
     determinants
    0.43
    Activations Density 0.000%

    No Known Activations