© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38137
    Prev
    Next
    INDEX
    Explanations

    REMEMBER

    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
    ur
    1.00
    tions
    0.99
    al
    0.95
    as
    0.89
    k
    0.86
    ون
    0.82
    tı
    0.82
    ri
    0.80
    or
    0.79
    f
    0.78
    POSITIVE LOGITS
     กัน
    0.66
     Museum
    0.63
     Memory
    0.59
    。
    0.57
     models
    0.57
     Board
    0.57
    การ
    0.57
     Code
    0.57
     สม
    0.57
     Magic
    0.55
    Activations Density 0.000%

    No Known Activations