© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138743
    Prev
    Next
    INDEX
    Explanations

    power output and productivity

    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_12_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
    اك
    0.44
    Боль
    0.43
    dogs
    0.43
    氨
    0.41
    ر
    0.41
     arthritis
    0.40
    История
    0.40
    WORD
    0.40
    鳞
    0.40
    isión
    0.40
    POSITIVE LOGITS
     st
    0.46
     stai
    0.45
     serve
    0.44
     săn
    0.42
     certify
    0.42
     posso
    0.42
     paddles
    0.41
     share
    0.41
     hazards
    0.40
     standard
    0.40
    Activations Density 0.001%

    No Known Activations