© 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. 154640
    Prev
    Next
    INDEX
    Explanations

    pork cutlet

    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
     P
    0.47
    P
    0.45
     Patch
    0.45
    patch
    0.44
    Patch
    0.43
    צי
    0.42
    Street
    0.40
    পট
    0.39
    Planning
    0.38
    ೈಸ
    0.37
    POSITIVE LOGITS
    カル
    0.54
    上が
    0.49
     cale
    0.46
     cal
    0.43
     calma
    0.42
    絣
    0.42
     CAL
    0.41
     Har
    0.40
     tern
    0.40
    上来
    0.39
    Activations Density 0.002%

    No Known Activations