© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35793
    Prev
    Next
    INDEX
    Explanations

    choose one or quote

    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_11_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
    م
    0.82
    מ
    0.72
    m
    0.64
    utenants
    0.60
    м
    0.59
     Parrish
    0.58
    म
    0.57
     '',
    0.56
     DJs
    0.56
    т
    0.56
    POSITIVE LOGITS
    的新
    0.62
    ٥
    0.57
    できます
    0.55
    '
    0.55
    芽
    0.55
    шена
    0.52
    وم
    0.52
     मिला
    0.52
    拭
    0.52
    衛生
    0.51
    Activations Density 0.004%

    No Known Activations