© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 238673
    Prev
    Next
    INDEX
    Explanations

    are left

    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_32_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
    policy
    0.38
     ब्रे
    0.37
    Linking
    0.37
    Growing
    0.36
    羸
    0.36
    growing
    0.35
     Growing
    0.35
    ﺄ
    0.35
    BuildAction
    0.35
    Lak
    0.35
    POSITIVE LOGITS
     selten
    0.40
     oligonucle
    0.39
     insist
    0.38
    KHTML
    0.37
     UCI
    0.37
    σκεται
    0.37
    ሚ
    0.37
     ReturnVal
    0.36
     inpatient
    0.36
    UCI
    0.36
    Activations Density 0.002%

    No Known Activations