© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211837
    Prev
    Next
    INDEX
    Explanations

    data science and medium.com

    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_20_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
     경우
    0.27
     ידי
    0.25
     sehingga
    0.25
     위해
    0.25
     通过
    0.24
     או
    0.24
    線
    0.24
     分析
    0.24
     する
    0.24
     consider
    0.24
    POSITIVE LOGITS
     Schae
    0.26
    ţiile
    0.24
    ਧ
    0.24
    ometh
    0.23
    हिट
    0.23
    itabbo
    0.23
    getRadius
    0.23
    হতের
    0.22
     odour
    0.22
     gült
    0.22
    Activations Density 0.000%

    No Known Activations