© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138992
    Prev
    Next
    INDEX
    Explanations

    elaborate explanation

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    otis
    0.46
     stort
    0.40
     
    0.38
    
    0.37
    OTO
    0.37
    agos
    0.36
    нё
    0.36
     desco
    0.35
    )";
    0.35
     renormalized
    0.35
    POSITIVE LOGITS
     zéro
    0.40
     yours
    0.40
     кв
    0.39
     anything
    0.38
     something
    0.38
     ZERO
    0.37
     tentativa
    0.37
     the
    0.36
     this
    0.36
     موس
    0.36
    Activations Density 0.075%

    No Known Activations