© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142812
    Prev
    Next
    INDEX
    Explanations

    technical instructions

    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_46_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
    Fun
    0.57
     Fun
    0.52
     F
    0.47
     FUN
    0.44
    روف
    0.41
     fun
    0.41
    F
    0.41
    Бан
    0.39
    藓
    0.39
    функ
    0.39
    POSITIVE LOGITS
    itchie
    0.43
    arg
    0.39
    IDC
    0.39
     arginine
    0.39
    ít
    0.38
     Ising
    0.38
    itev
    0.38
    贬
    0.38
    ㄑ
    0.38
    iter
    0.37
    Activations Density 0.030%

    No Known Activations