© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35320
    Prev
    Next
    INDEX
    Explanations

    embedded in

    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
    {
    0.84
    I
    0.69
     for
    0.61
     produce
    0.61
     distance
    0.60
     ResponseEntity
    0.60
     proportionately
    0.59
     WITHIN
    0.57
    al
    0.55
     kalah
    0.55
    POSITIVE LOGITS
    지만
    0.87
    م
    0.77
    ج
    0.77
    도
    0.77
    خ
    0.73
    在
    0.72
    a
    0.69
    나
    0.69
    기를
    0.68
    ного
    0.68
    Activations Density 0.001%

    No Known Activations