© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101248
    Prev
    Next
    INDEX
    Explanations

    step up in quality

    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_14_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
    ފ
    0.61
    en
    0.58
    ᱵ
    0.54
     रोपवे
    0.53
     عملی
    0.52
     theories
    0.51
     কাহারও
    0.51
     इतिहासकारों
    0.50
    蹉
    0.50
     follicles
    0.50
    POSITIVE LOGITS
     направи
    0.50
    чане
    0.50
    ዎን
    0.48
     घर
    0.47
     interpreter
    0.46
    োর্স
    0.46
    }^{+},
    0.46
     און
    0.46
     courte
    0.45
     къ
    0.44
    Activations Density 0.001%

    No Known Activations