© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115601
    Prev
    Next
    INDEX
    Explanations

    insulin effectiveness

    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_27_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
     Faith
    0.43
    Faith
    0.37
     Albums
    0.36
     Original
    0.36
     grateful
    0.36
    轼
    0.35
     Tricks
    0.34
     Faithful
    0.34
    arser
    0.34
     Networks
    0.34
    POSITIVE LOGITS
    ковой
    0.42
    க்கல்
    0.41
     ribosome
    0.40
     `./
    0.39
     razor
    0.39
    اوی
    0.39
    皙
    0.39
     zasad
    0.38
    ƾ
    0.38
     knife
    0.38
    Activations Density 0.000%

    No Known Activations