© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216929
    Prev
    Next
    INDEX
    Explanations

    Indigenous peoples and languages

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    Kh
    0.53
     Kh
    0.50
    Kan
    0.50
    kh
    0.46
     Bg
    0.46
     kan
    0.45
    ข
    0.44
     Kan
    0.44
    カン
    0.42
    Dg
    0.42
    POSITIVE LOGITS
     Kal
    0.46
     kal
    0.45
    aust
    0.43
     Aust
    0.43
    Aust
    0.42
     v
    0.42
    Processed
    0.41
     Neust
    0.40
     glab
    0.39
     KAL
    0.39
    Activations Density 0.001%

    No Known Activations