© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225806
    Prev
    Next
    INDEX
    Explanations

    finally followed by action or result

    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_10_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
     ка
    0.77
    ем
    0.75
    사
    0.75
    ul
    0.73
     cleansed
    0.72
     ци
    0.70
    দ
    0.70
     т
    0.68
     كتب
    0.68
     أك
    0.67
    POSITIVE LOGITS
     Alloys
    0.73
    =
    0.69
     Shipping
    0.66
     Families
    0.66
     Arthritis
    0.66
    IAMS
    0.65
     DHL
    0.65
     TRADE
    0.64
     Kidney
    0.64
     Biodiversity
    0.64
    Activations Density 0.003%

    No Known Activations