© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59552
    Prev
    Next
    INDEX
    Explanations

    electrostatic

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     electro
    1.58
    electro
    1.46
     Electro
    1.42
    Electro
    1.39
     NA
    1.23
    NA
    1.12
     NAA
    1.09
    ナ
    1.05
     NAC
    1.04
     elektro
    1.04
    POSITIVE LOGITS
     electrostatic
    1.23
     Coulomb
    0.61
     ESD
    0.49
     coulomb
    0.48
    ESD
    0.46
     Woodstock
    0.38
     Es
    0.38
    어
    0.36
     Grunge
    0.34
    Coul
    0.34
    Activations Density 0.053%

    No Known Activations