© 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. 129657
    Prev
    Next
    INDEX
    Explanations

    membrane potential

    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
     from
    1.24
     (
    1.23
    H
    1.16
     be
    1.14
    K
    1.09
    te
    1.09
    M
    1.07
    O
    1.07
    D
    1.06
    B
    1.06
    POSITIVE LOGITS
    ला
    1.17
    تها
    1.15
    る
    1.13
    ח
    1.13
    ्स
    1.07
    স
    1.06
    ج
    1.06
    ሳሪያ
    1.04
    но
    1.01
    ur
    0.99
    Activations Density 0.002%

    No Known Activations