© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48433
    Prev
    Next
    INDEX
    Explanations

    terms weeks all

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     পরও
    0.38
     거고
    0.38
     appropriation
    0.37
    選手権
    0.37
     대로
    0.37
     ​​
    0.36
     utensils
    0.36
    <unused2222>
    0.36
     silverware
    0.36
    versive
    0.36
    POSITIVE LOGITS
    all
    0.56
    तरह
    0.56
    থেকে
    0.52
    কারণ
    0.52
    words
    0.51
    order
    0.50
    not
    0.49
    about
    0.48
    terms
    0.47
    weeks
    0.47
    Activations Density 0.015%

    No Known Activations