© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36493
    Prev
    Next
    INDEX
    Explanations

    step inside

    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_11_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
    ق
    0.77
    안녕하세요
    0.68
    سلام
    0.67
    ب
    0.66
    സി
    0.63
    По
    0.63
    Vous
    0.63
    Acet
    0.61
    الأ
    0.61
    utils
    0.60
    POSITIVE LOGITS
     została
    0.62
     mountain
    0.57
     deferred
    0.57
    u
    0.57
     wrath
    0.55
     tomato
    0.54
     collided
    0.54
     moto
    0.54
    ed
    0.53
     други
    0.53
    Activations Density 0.000%

    No Known Activations