© 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. 29956
    Prev
    Next
    INDEX
    Explanations

    remain at a state

    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
    न्दावन
    0.37
    를
    0.37
     часть
    0.36
     hạng
    0.35
    მასრულ
    0.35
     pillars
    0.35
     orchards
    0.35
    ᵚ
    0.34
     ಮನೆ
    0.33
    󰡔
    0.33
    POSITIVE LOGITS
    ing
    0.66
    an
    0.64
    u
    0.63
    im
    0.59
    ä
    0.55
    f
    0.53
    is
    0.52
    a
    0.51
    ap
    0.49
    ad
    0.49
    Activations Density 0.008%

    No Known Activations