© 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. 36983
    Prev
    Next
    INDEX
    Explanations

    never mind

    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
    Negative Logits
    埸
    0.32
     تبدی
    0.31
    Ⅽ
    0.31
    𒈨
    0.31
     nichts
    0.30
    াবির
    0.30
    婪
    0.30
    غو
    0.30
     keinen
    0.30
     algoritmo
    0.29
    POSITIVE LOGITS
     sometimes
    0.36
    Sometimes
    0.34
     अक्सर
    0.33
    sometimes
    0.31
    有时候
    0.31
     g
    0.30
     genellikle
    0.30
     Sometimes
    0.30
     trips
    0.30
     important
    0.29
    Activations Density 0.002%

    No Known Activations