© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170581
    Prev
    Next
    INDEX
    Explanations

    temporal sequencing

    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_20_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
     aceite
    0.38
    腸
    0.37
     compartmental
    0.36
     डाइजेस्टिव
    0.36
    리와
    0.36
    肠
    0.36
     చేశాడు
    0.35
     鳥
    0.35
     Rivers
    0.35
     deferred
    0.35
    POSITIVE LOGITS
    alur
    0.38
     japanese
    0.37
    դ
    0.37
    rophy
    0.36
     unve
    0.36
     ۳
    0.36
    gren
    0.36
     offending
    0.35
     ሃ
    0.35
     fos
    0.34
    Activations Density 0.010%

    No Known Activations