© 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. 36707
    Prev
    Next
    INDEX
    Explanations

    software development

    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
    ス
    0.73
    с
    0.73
    0.71
    д
    0.70
    6
    0.66
    e
    0.65
    ↵
    0.64
    was
    0.64
    те
    0.63
    were
    0.63
    POSITIVE LOGITS
    ق
    0.64
    ج
    0.59
    ிஸ்த
    0.58
     the
    0.57
    *;
    0.57
    conto
    0.57
    bilt
    0.57
     of
    0.56
    مین
    0.56
    [%
    0.55
    Activations Density 0.005%

    No Known Activations