© 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. 221459
    Prev
    Next
    INDEX
    Explanations

    True/False choices

    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
     అందుకు
    0.38
    مک
    0.38
    રી
    0.36
    IPSET
    0.36
    캠
    0.36
    စွာ
    0.35
     eliminación
    0.35
    欉
    0.34
    证券投资基金
    0.34
    ExternalTaskPojo
    0.34
    POSITIVE LOGITS
     Seq
    0.41
     do
    0.38
     du
    0.37
     daqu
    0.37
     office
    0.36
     kum
    0.36
    isio
    0.36
     stays
    0.35
     sper
    0.35
     Hoffman
    0.35
    Activations Density 0.000%

    No Known Activations