© 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. 12558
    Prev
    Next
    INDEX
    Explanations

    lights and fans

    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
     Leibnitz
    0.47
    コント
    0.45
     Encryption
    0.45
    手指
    0.44
    约
    0.44
     Lisa
    0.44
    ম্বা
    0.44
     ඔබට
    0.44
     Garvey
    0.43
    选
    0.43
    POSITIVE LOGITS
    ored
    0.43
     illuminating
    0.42
    +},
    0.41
    ’
    0.40
    τητα
    0.40
    ice
    0.40
    ether
    0.39
     overhead
    0.39
     illum
    0.39
     КО
    0.38
    Activations Density 0.021%

    No Known Activations