© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 214263
    Prev
    Next
    INDEX
    Explanations

    code development

    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_43_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
     فط
    0.42
    <0xA6>
    0.39
    Main
    0.39
    მართ
    0.38
     yin
    0.37
    法施行令
    0.37
     Polynesia
    0.37
     کمتر
    0.37
    함
    0.37
     ै
    0.36
    POSITIVE LOGITS
    yscrapers
    0.40
     SLO
    0.38
     RGB
    0.34
     Pp
    0.34
     p
    0.33
    ージ
    0.33
     C
    0.33
     sĩ
    0.32
    тран
    0.32
    SystemCall
    0.32
    Activations Density 0.000%

    No Known Activations