© 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. 31781
    Prev
    Next
    INDEX
    Explanations

    key business elements

    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
     รุ่น
    0.39
    였다
    0.39
     модели
    0.39
    였
    0.39
    聵
    0.38
    BES
    0.37
     lingkaran
    0.37
    钅
    0.37
     Modelle
    0.37
     हवा
    0.36
    POSITIVE LOGITS
    TRIG
    0.41
    Right
    0.41
     Advantages
    0.40
     Packages
    0.39
     TRIG
    0.39
     Exhib
    0.38
     Skills
    0.37
    So
    0.36
     OJ
    0.36
    草原
    0.36
    Activations Density 0.002%

    No Known Activations