© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154093
    Prev
    Next
    INDEX
    Explanations

    assorted colors and sizes

    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_23_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
     گفتگو
    0.40
     Instance
    0.38
     accompan
    0.37
    の一部
    0.36
     유
    0.36
     полной
    0.36
     уча
    0.36
     هنگام
    0.36
     গুণ
    0.35
    アラ
    0.35
    POSITIVE LOGITS
    齜
    0.50
    তরাং
    0.48
    ậy
    0.45
    setup
    0.44
    trasound
    0.43
     sidelined
    0.43
    slider
    0.43
    স্পতিবার
    0.42
     tiger
    0.42
    tiger
    0.42
    Activations Density 0.000%

    No Known Activations