© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11316
    Prev
    Next
    INDEX
    Explanations

    chiaroscuro lighting effects

    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_13_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
    org
    0.41
    osp
    0.38
    osság
    0.38
    з
    0.37
    端
    0.36
    CCP
    0.36
    مت
    0.36
    стям
    0.36
    л
    0.36
    ዝ
    0.36
    POSITIVE LOGITS
     conhecer
    0.43
     exercer
    0.43
     unsere
    0.41
     سە
    0.41
     сделать
    0.40
     cushion
    0.40
    CurrentByte
    0.39
     estabelecer
    0.39
     publice
    0.39
    ᶤ
    0.39
    Activations Density 0.015%

    No Known Activations