© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206741
    Prev
    Next
    INDEX
    Explanations

    Hindi question words

    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_10_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
    ್ಟ
    0.59
     Вол
    0.58
    GEN
    0.57
     ван
    0.57
     Antibodies
    0.55
    \}$.
    0.55
     liczb
    0.55
     comptes
    0.55
     tasas
    0.54
    <unused332>
    0.54
    POSITIVE LOGITS
     adhes
    0.54
    ları
    0.53
     smoking
    0.53
    Symfony
    0.53
    nya
    0.52
     cosplay
    0.51
     shutdown
    0.50
     fester
    0.50
    endment
    0.49
    larına
    0.49
    Activations Density 0.000%

    No Known Activations