© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14242
    Prev
    Next
    INDEX
    Explanations

    time spent doing activities

    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_13_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
    Y
    0.42
    B
    0.34
    L
    0.33
    5
    0.32
     innermost
    0.31
    fr
    0.31
     Wunsch
    0.31
    F
    0.31
    U
    0.31
    迎え
    0.30
    POSITIVE LOGITS
    ário
    0.38
     ASE
    0.34
     analisar
    0.33
    㖑
    0.33
     ஆலோசனை
    0.32
     canaliculato
    0.31
    এসই
    0.31
    RichEmbed
    0.31
     metaphors
    0.31
    㡀
    0.30
    Activations Density 0.000%

    No Known Activations