© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167791
    Prev
    Next
    INDEX
    Explanations

    he/she/it noticed

    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_31_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
    層
    0.38
     Microsoft
    0.37
     AVG
    0.34
    Microsoft
    0.33
    趟
    0.32
     Around
    0.32
    ウォ
    0.32
    蝦
    0.32
     Encoder
    0.31
     Fry
    0.31
    POSITIVE LOGITS
     अनुमोदन
    0.35
     kommer
    0.34
     approbation
    0.33
    காற்று
    0.33
     komma
    0.33
     potvr
    0.32
     ›
    0.32
     Роз
    0.32
     rozum
    0.32
     permiss
    0.31
    Activations Density 0.003%

    No Known Activations