© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177259
    Prev
    Next
    INDEX
    Explanations

    two or more

    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_24_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
     على
    0.49
     på
    0.48
     electrom
    0.47
     casi
    0.44
     nie
    0.43
     e
    0.43
     daca
    0.42
     асо
    0.41
     roky
    0.41
     eje
    0.41
    POSITIVE LOGITS
    篒
    0.47
     मंजिल
    0.43
     टेंस
    0.39
    ⚌
    0.39
    osition
    0.38
     quizz
    0.38
    akkhanam
    0.38
     Anu
    0.38
    ታል
    0.37
    apabb
    0.37
    Activations Density 0.000%

    No Known Activations