© 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. 232343
    Prev
    Next
    INDEX
    Explanations

    inspire confidence and interest

    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
    Not in Any Lists

    No Comments

    Negative Logits
     caution
    0.39
    Caution
    0.38
     careful
    0.38
    ലീസ്
    0.37
    嬸
    0.37
     препо
    0.36
     усили
    0.36
     Anosov
    0.36
    Detal
    0.36
     demonstrate
    0.36
    POSITIVE LOGITS
     Kalian
    0.39
     conden
    0.39
     viewport
    0.38
    銮
    0.38
    浲
    0.38
    foaf
    0.36
     Vent
    0.36
     flowed
    0.36
    modelVersion
    0.35
    idir
    0.35
    Activations Density 0.001%

    No Known Activations