© 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. 87722
    Prev
    Next
    INDEX
    Explanations

    block chaining

    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
     I
    0.59
    il
    0.58
    áticos
    0.56
    签
    0.52
    خص
    0.50
     lingkaran
    0.50
     mutations
    0.49
    法施行令
    0.49
    InputBorder
    0.49
    orts
    0.49
    POSITIVE LOGITS
    د
    0.94
    to
    0.86
    ры
    0.77
    з
    0.77
    l
    0.75
    ру
    0.75
    {
    0.75
    ם
    0.74
    ри
    0.72
    is
    0.72
    Activations Density 0.001%

    No Known Activations