© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109462
    Prev
    Next
    INDEX
    Explanations

    automation, quotation, optation, silylation

    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_2_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
     I
    0.97
     (
    0.75
    r
    0.75
    ar
    0.72
    l
    0.72
     A
    0.69
    0.66
    in
    0.63
    I
    0.62
     T
    0.61
    POSITIVE LOGITS
    ка
    0.81
    :
    0.70
    но
    0.66
    :‏
    0.57
    на
    0.56
     ос
    0.55
     помочь
    0.55
    ુ
    0.55
    ः
    0.55
     он
    0.54
    Activations Density 0.000%

    No Known Activations