© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44229
    Prev
    Next
    INDEX
    Explanations

    florets or dress

    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_3_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
    н
    0.79
    ב
    0.79
    その
    0.76
    ری
    0.74
    т
    0.73
    ш
    0.71
    נ
    0.71
    اد
    0.71
    и
    0.71
    وری
    0.70
    POSITIVE LOGITS
    s
    1.18
    on
    0.87
    u
    0.85
    t
    0.79
    in
    0.75
    ain
    0.72
    ↵
    0.71
    er
    0.70
    ations
    0.69
    ens
    0.68
    Activations Density 0.009%

    No Known Activations