© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18170
    Prev
    Next
    INDEX
    Explanations

    jQuery library scripts

    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_40_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
     Fourteen
    0.45
     tablespoons
    0.42
     sumber
    0.41
     Fifteen
    0.40
     Thirteen
    0.40
    冲
    0.40
     চেন
    0.39
     Eleven
    0.39
    цен
    0.38
     THREE
    0.37
    POSITIVE LOGITS
    ᵚ
    0.37
    јо
    0.36
     Punjabi
    0.36
    ሳይ
    0.35
    networking
    0.35
     jär
    0.35
     menet
    0.35
    埼
    0.35
    閬
    0.35
    리지
    0.35
    Activations Density 0.000%

    No Known Activations