© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50288
    Prev
    Next
    INDEX
    Explanations

    collarbone

    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_10_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
    s
    0.19
    ye
    0.15
    yi
    0.14
    ke
    0.14
    о
    0.14
    ים
    0.13
    ियां
    0.13
    yb
    0.13
    APOLIS
    0.13
    ্য
    0.13
    POSITIVE LOGITS
     as
    0.16
     Trouble
    0.15
     primi
    0.15
     magia
    0.15
    他の
    0.14
    टाइम
    0.14
     dificultades
    0.14
     pneumatic
    0.14
    даги
    0.14
    ﺗ
    0.14
    Activations Density 0.008%

    No Known Activations