© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1360
    Prev
    Next
    INDEX
    Explanations

    lines, plastic, Tilt

    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_39_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
     হইয়াছিলেন
    0.30
    射
    0.30
     রেশন
    0.27
     አስተ
    0.27
     xạ
    0.26
     बेसब
    0.26
    uclease
    0.26
     morphisms
    0.26
    είο
    0.26
    初始化
    0.25
    POSITIVE LOGITS
     ¾
    0.30
     jump
    0.28
     builds
    0.27
     bât
    0.27
     ½
    0.27
     leaders
    0.27
     hook
    0.27
     jumped
    0.27
     barr
    0.27
     bra
    0.27
    Activations Density 0.082%

    No Known Activations