© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 210720
    Prev
    Next
    INDEX
    Explanations

    now

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
    賴
    0.42
    諺
    0.41
    HIB
    0.39
    ală
    0.38
    赫
    0.38
    গুলিতে
    0.37
    荇
    0.37
     Actualmente
    0.37
    HX
    0.37
    Ꮋ
    0.37
    POSITIVE LOGITS
     undet
    0.38
    ulations
    0.38
    indel
    0.38
     eliminar
    0.38
     najleps
    0.38
    ocr
    0.37
     remove
    0.37
    వర
    0.37
    utet
    0.36
    विरो
    0.36
    Activations Density 0.001%

    No Known Activations