© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248408
    Prev
    Next
    INDEX
    Explanations

    sun

    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_56_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
    連
    0.97
    连
    0.82
     連
    0.71
     연
    0.67
    ض
    0.59
    연
    0.56
    就连
    0.55
     liên
    0.50
     Yeon
    0.49
    而已
    0.39
    POSITIVE LOGITS
     sol
    3.92
    Sol
    3.33
     Sol
    3.28
    sol
    3.19
     SOL
    2.69
     솔
    2.69
    솔
    2.53
     сол
    2.30
    SOL
    2.30
     sols
    2.13
    Activations Density 0.036%

    No Known Activations