© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87908
    Prev
    Next
    INDEX
    Explanations

    wildcard or file pattern matching

    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_3_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
     dlatego
    0.79
     ۴
    0.76
    オン
    0.74
     اړه
    0.73
    行った
    0.72
     dola
    0.72
    行く
    0.72
     раствор
    0.71
     кораб
    0.70
     anál
    0.70
    POSITIVE LOGITS
    s
    1.34
    of
    0.96
    RA
    0.89
    z
    0.88
    ade
    0.83
    ans
    0.82
    ach
    0.82
    ode
    0.81
    ur
    0.80
    CR
    0.80
    Activations Density 0.012%

    No Known Activations