© 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. 200566
    Prev
    Next
    INDEX
    Explanations

    encycl

    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
    OC
    0.39
    ノ
    0.38
    QUAL
    0.37
     Es
    0.35
    enos
    0.35
    Es
    0.35
     neka
    0.34
     junction
    0.34
     inflicted
    0.34
    qua
    0.34
    POSITIVE LOGITS
     Animator
    0.42
    ShoppingCart
    0.42
    嚆
    0.42
     Bo
    0.41
    Barn
    0.40
    颊
    0.40
    囱
    0.39
     образом
    0.39
     Garn
    0.39
     Begriff
    0.39
    Activations Density 0.000%

    No Known Activations