© 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. 46233
    Prev
    Next
    INDEX
    Explanations

    this refers to

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ことがあります
    0.34
    nf
    0.34
    纪
    0.34
     состоя
    0.33
     materially
    0.33
     uitvo
    0.32
     vibr
    0.32
     introduce
    0.31
    之际
    0.31
    iają
    0.31
    POSITIVE LOGITS
    Twins
    0.39
     Netzwerk
    0.36
    ็ด
    0.35
     Twins
    0.35
     FileManager
    0.35
    鶚
    0.34
     Primeiro
    0.33
    缙
    0.33
    𝗞
    0.33
     Hickman
    0.33
    Activations Density 0.065%

    No Known Activations