© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167443
    Prev
    Next
    INDEX
    Explanations

    drawing commands and coordinates

    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_34_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
     Up
    0.40
     Murray
    0.40
     ре
    0.39
     MUR
    0.38
     mur
    0.38
     кое
    0.38
    岦
    0.38
     biên
    0.37
     zwe
    0.36
     Clair
    0.36
    POSITIVE LOGITS
    碑
    0.42
     ठहरा
    0.40
     stops
    0.38
     chạm
    0.38
    enches
    0.38
    阻止
    0.36
     blames
    0.36
    လုံး
    0.36
    甪
    0.35
    LEG
    0.35
    Activations Density 0.003%

    No Known Activations