© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10570
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and environments

    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
    孛
    0.29
    लब
    0.29
     материа
    0.28
    alma
    0.28
    栆
    0.28
     personalized
    0.28
    Lifetime
    0.28
     नक
    0.28
    adeso
    0.28
    cesis
    0.28
    POSITIVE LOGITS
     frequência
    0.32
     वाइड
    0.32
     Fade
    0.31
    ubov
    0.31
    プレート
    0.30
     elektr
    0.30
     Wir
    0.30
     fade
    0.30
    徵
    0.29
     Faiz
    0.29
    Activations Density 0.001%

    No Known Activations