© 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. 36757
    Prev
    Next
    INDEX
    Explanations

    AI capabilities and generation

    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
    0.95
    kons
    0.67
     북
    0.66
    F
    0.64
    Titanic
    0.63
    new
    0.62
    కు
    0.61
    can
    0.60
     दुस
    0.60
    C
    0.59
    POSITIVE LOGITS
    ق
    0.75
     micrograph
    0.70
     welke
    0.69
     subheading
    0.68
     weighty
    0.66
    3
    0.66
     mitten
    0.65
     Schweizer
    0.65
    ور
    0.64
    εν
    0.63
    Activations Density 0.109%

    No Known Activations