© 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. 35653
    Prev
    Next
    INDEX
    Explanations

    code or programming

    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
     unbek
    0.35
    ONY
    0.33
    ;
    0.33
     व्हा
    0.33
    ETA
    0.33
    twitch
    0.32
    ói
    0.32
    ETER
    0.32
    𝒋
    0.31
    ִי
    0.30
    POSITIVE LOGITS
     Chapman
    0.33
     والمر
    0.33
     shovel
    0.32
     McClure
    0.32
    ئ
    0.32
     てる
    0.31
     landslide
    0.31
     ions
    0.30
     Burke
    0.30
     Learning
    0.30
    Activations Density 0.018%

    No Known Activations