© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34228
    Prev
    Next
    INDEX
    Explanations

    Tamil Nadu

    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
     प
    0.54
     پ
    0.47
     pâ
    0.44
     eigenlijk
    0.42
     pname
    0.42
     প্যা
    0.42
     पंकज
    0.41
    istici
    0.41
     equilib
    0.41
    प
    0.41
    POSITIVE LOGITS
     S
    0.61
    ச்
    0.57
     v
    0.50
     வ
    0.48
     V
    0.46
     s
    0.44
    ச்ச
    0.44
     SNR
    0.44
     ச
    0.44
    SSR
    0.43
    Activations Density 0.002%

    No Known Activations