© 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. 101654
    Prev
    Next
    INDEX
    Explanations

    API, SKUs, units, interfaces

    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
     നിന്ന്
    0.42
     कॉम
    0.38
     इसे
    0.38
    katana
    0.38
    νων
    0.37
    పోయే
    0.37
    笥
    0.37
    Casa
    0.36
    █
    0.36
    doped
    0.35
    POSITIVE LOGITS
     attaques
    0.50
     radiographs
    0.45
     sutures
    0.45
     headwinds
    0.42
     convolutions
    0.42
     orbits
    0.41
    ری
    0.41
     deployments
    0.41
     opérations
    0.41
    örungen
    0.41
    Activations Density 0.060%

    No Known Activations