© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40394
    Prev
    Next
    INDEX
    Explanations

    AI agents and systems

    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_11_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
     охра
    0.46
    w
    0.43
    s
    0.40
     Cold
    0.40
     W
    0.40
     Guardian
    0.40
     Agri
    0.39
     AG
    0.39
     гар
    0.38
     waf
    0.38
    POSITIVE LOGITS
    ۶
    0.42
    plates
    0.39
    ٥
    0.38
     ఆలో
    0.38
    🔛
    0.38
    ستون
    0.38
    rootScope
    0.37
    윳
    0.37
    platten
    0.37
    ሯ
    0.37
    Activations Density 0.104%

    No Known Activations