© 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. 36766
    Prev
    Next
    INDEX
    Explanations

    point of view

    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
    5
    0.83
    ।
    0.79
    س
    0.77
     for
    0.73
    A
    0.73
    。
    0.73
    د
    0.70
    де
    0.68
    एस
    0.68
    봤
    0.68
    POSITIVE LOGITS
    ng
    0.73
    min
    0.67
    listar
    0.58
    ουσ
    0.57
    மான்
    0.55
    sef
    0.54
     reação
    0.54
    setNome
    0.54
    v
    0.54
     ০৯
    0.54
    Activations Density 0.001%

    No Known Activations