© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83098
    Prev
    Next
    INDEX
    Explanations

    divide by a number

    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_29_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
    |+|
    0.30
     môžu
    0.30
     bou
    0.29
     podría
    0.29
     houdt
    0.29
     könnten
    0.28
     potentially
    0.28
     можуть
    0.28
     efficiently
    0.28
     maken
    0.28
    POSITIVE LOGITS
    Lastly
    0.31
    politics
    0.31
    Politics
    0.30
    political
    0.29
    avacanam
    0.29
    艮
    0.29
     Menurut
    0.29
    quando
    0.28
     Politics
    0.28
    ຂອງ
    0.28
    Activations Density 0.008%

    No Known Activations