© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41131
    Prev
    Next
    INDEX
    Explanations

    discarding uncommitted changes

    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_22_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
     population
    0.46
     elsewhere
    0.44
     populations
    0.43
     expansions
    0.42
    borrow
    0.42
     newspapers
    0.42
    +/-
    0.41
     dans
    0.41
    /**
    0.40
     bowls
    0.40
    POSITIVE LOGITS
    теру
    0.51
     உயர்
    0.44
    𒃶
    0.42
    ТЕ
    0.41
    थर
    0.41
     પરી
    0.41
     নেত
    0.40
     mengubah
    0.40
     рит
    0.40
    解釋
    0.40
    Activations Density 0.001%

    No Known Activations