© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132870
    Prev
    Next
    INDEX
    Explanations

    Yes

    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_50_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
     ea
    0.59
    ea
    0.54
    EA
    0.47
     Ea
    0.47
     EA
    0.42
     EAC
    0.42
    elles
    0.42
    判
    0.42
    oe
    0.40
    uan
    0.39
    POSITIVE LOGITS
    чник
    0.43
     Lux
    0.43
    InsertInt
    0.42
    Lux
    0.41
     Mil
    0.40
     Luz
    0.40
     circuits
    0.39
     Liv
    0.39
     lux
    0.39
    แข
    0.39
    Activations Density 0.003%

    No Known Activations