© 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. 241701
    Prev
    Next
    INDEX
    Explanations

    lab followed by module or software name

    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
    vrdr
    0.40
    วิต
    0.39
    麿
    0.39
    linewidth
    0.37
     갑
    0.37
     Saj
    0.37
     ليه
    0.37
    udia
    0.36
     слад
    0.36
    ડિયા
    0.36
    POSITIVE LOGITS
    容
    0.40
    closing
    0.40
     closing
    0.39
    Closing
    0.39
     Closing
    0.37
    Kok
    0.37
     Schle
    0.36
     oluştur
    0.36
     civil
    0.34
     созда
    0.34
    Activations Density 0.000%

    No Known Activations