© 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. 43356
    Prev
    Next
    INDEX
    Explanations

    film types and photography

    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
    es
    0.68
    ES
    0.63
     African
    0.60
     dicho
    0.56
     grayscale
    0.56
     repas
    0.56
     Σ
    0.55
     Mejor
    0.55
     situado
    0.54
     Strengthen
    0.54
    POSITIVE LOGITS
    Dest
    0.52
    Cameras
    0.51
    中国人
    0.49
    cameras
    0.48
    영상
    0.47
    완
    0.47
    ዖ
    0.47
    ством
    0.46
    डे
    0.46
     nowDate
    0.46
    Activations Density 0.002%

    No Known Activations