© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104467
    Prev
    Next
    INDEX
    Explanations

    brevetoxin, saxitoxin, domoic acid

    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_1_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
    '
    1.91
     is
    1.80
    {
    1.55
    (
    1.52
    .
    1.51
     was
    1.41
    s
    1.35
    \
    1.34
     has
    1.32
    on
    1.26
    POSITIVE LOGITS
    ни
    1.34
    ח
    1.33
    он
    1.28
    ן
    1.21
    ன்
    1.16
    ون
    1.06
    ம்
    1.05
    ้
    1.05
    йки
    1.05
    ่
    1.03
    Activations Density 0.000%

    No Known Activations