© 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. 154995
    Prev
    Next
    INDEX
    Explanations

    food

    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
     erro
    0.42
    ROY
    0.39
    gridLayout
    0.38
    зульта
    0.38
    ప్ర
    0.37
    ཚ
    0.37
     basePath
    0.36
     soport
    0.36
    ယ်
    0.35
    Cleared
    0.35
    POSITIVE LOGITS
     mech
    0.42
     Mech
    0.41
     incógn
    0.40
    Mech
    0.39
     mest
    0.38
    Mechan
    0.38
     MEGA
    0.38
    pixel
    0.38
    Ễ
    0.38
    ématique
    0.38
    Activations Density 0.001%

    No Known Activations