© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199829
    Prev
    Next
    INDEX
    Explanations

    necessities

    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_12_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
    ée
    0.53
     menambahkan
    0.49
     Bootstrap
    0.48
     utilizes
    0.46
     TensorFlow
    0.46
     Bronco
    0.46
     formulaire
    0.45
    蛲
    0.45
     Tensor
    0.44
     PAGE
    0.44
    POSITIVE LOGITS
    لات
    0.54
    к
    0.52
    ب
    0.52
    uera
    0.52
    ئ
    0.51
    نف
    0.51
    лод
    0.51
    лга
    0.49
    мер
    0.48
    ស្ល
    0.48
    Activations Density 0.000%

    No Known Activations