© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214842
    Prev
    Next
    INDEX
    Explanations

    hot

    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
    0.95
    P
    0.65
     p
    0.61
    setP
    0.57
    Ap
    0.55
    getP
    0.55
     پ
    0.55
     ap
    0.55
     Ap
    0.54
    ಪೆ
    0.52
    POSITIVE LOGITS
     HOT
    0.43
    HOT
    0.42
    Toilet
    0.39
     underestimates
    0.39
     neden
    0.39
    hot
    0.38
    Hot
    0.38
    lic
    0.38
     hot
    0.38
     cumpl
    0.37
    Activations Density 0.005%

    No Known Activations