© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174122
    Prev
    Next
    INDEX
    Explanations

    similar size or category

    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
     sociales
    0.37
     बॅ
    0.35
     philosoph
    0.35
     バ
    0.34
    āk
    0.33
     yesterday
    0.31
     facebook
    0.31
    ruk
    0.31
     رشته
    0.31
     identificado
    0.31
    POSITIVE LOGITS
     تعاون
    0.37
    軋
    0.36
     apert
    0.34
    螈
    0.33
     réalis
    0.33
     Treatments
    0.33
     realization
    0.33
    Dependencies
    0.33
     Argonne
    0.33
     Variante
    0.33
    Activations Density 0.002%

    No Known Activations