© 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. 38248
    Prev
    Next
    INDEX
    Explanations

    diabetes

    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
    I
    0.88
    í
    0.86
    ar
    0.84
     I
    0.76
    ó
    0.74
    {
    0.73
     A
    0.73
    :
    0.70
    (
    0.64
    ich
    0.64
    POSITIVE LOGITS
     as
    1.06
    یت
    0.88
    ソ
    0.86
     bosonic
    0.81
    اری
    0.79
    میل
    0.78
     at
    0.78
    ন
    0.78
     goble
    0.76
    𝘴
    0.75
    Activations Density 0.000%

    No Known Activations