© 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. 221425
    Prev
    Next
    INDEX
    Explanations

    crazy or cursed

    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
    führ
    0.37
     Salv
    0.36
    銠
    0.35
    "?
    0.35
    sal
    0.34
    κτή
    0.34
     słu
    0.34
    violations
    0.34
     salvar
    0.33
     auctions
    0.33
    POSITIVE LOGITS
    ̝
    0.35
     Tade
    0.35
     seperate
    0.33
     Ambro
    0.32
     Miros
    0.32
    ूबी
    0.32
    myer
    0.32
    ществует
    0.31
     eres
    0.31
     Federated
    0.31
    Activations Density 0.000%

    No Known Activations