© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144778
    Prev
    Next
    INDEX
    Explanations

    Panel configurations

    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_0_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
    1.66
    м
    1.62
    й
    1.55
    ని
    1.45
    স
    1.41
    მწიფ
    1.30
    ৫
    1.29
    ח
    1.26
    ೫
    1.16
    이랑
    1.14
    POSITIVE LOGITS
    c
    1.93
    s
    1.91
    iv
    1.57
     can
    1.55
    t
    1.55
     is
    1.52
    g
    1.52
    ’
    1.47
    in
    1.46
    ob
    1.45
    Activations Density 0.000%

    No Known Activations