© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41648
    Prev
    Next
    INDEX
    Explanations

    formulas and calculations

    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_22_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
    म्मेदारी
    0.24
     टन
    0.23
     maž
    0.23
    emás
    0.23
    ឃើញ
    0.22
    сут
    0.22
    ኼ
    0.21
    Outstanding
    0.21
     patrimonio
    0.21
     majorité
    0.21
    POSITIVE LOGITS
    anyu
    0.22
     oder
    0.21
    ]["
    0.21
     किंवा
    0.20
     گوگل
    0.20
    '-
    0.20
    ン
    0.20
     Todd
    0.20
     alebo
    0.20
     ('
    0.20
    Activations Density 0.024%

    No Known Activations