© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246580
    Prev
    Next
    INDEX
    Explanations

    hypoglycemia and hyperglycemia

    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_40_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
     blur
    0.44
     総
    0.43
     death
    0.42
     stains
    0.41
     Siegfried
    0.41
    ட்டா
    0.40
     blinked
    0.40
     Blink
    0.40
     disease
    0.39
     bedroom
    0.39
    POSITIVE LOGITS
     mechanistic
    0.42
    {|\
    0.41
     MECHAN
    0.39
    mechan
    0.39
    quia
    0.39
    த்தர
    0.39
    REAT
    0.38
     mechan
    0.38
     механи
    0.38
     mecan
    0.37
    Activations Density 0.002%

    No Known Activations