© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171594
    Prev
    Next
    INDEX
    Explanations

    unsigned int boost net

    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_20_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
    isf
    0.43
     accol
    0.42
     vâ
    0.40
     가져
    0.38
    Handlers
    0.38
     +(
    0.38
     어느
    0.37
    im
    0.37
    άν
    0.36
    ्‍
    0.36
    POSITIVE LOGITS
    τική
    0.47
     MAGNET
    0.45
     پیپلز
    0.44
    lefthar
    0.43
    新技术
    0.42
     Inflammation
    0.41
     tecnologie
    0.41
    ρική
    0.41
    ർട്ട
    0.41
    噰
    0.41
    Activations Density 0.000%

    No Known Activations