© 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. 175812
    Prev
    Next
    INDEX
    Explanations

    gray

    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
    Suk
    0.42
    nment
    0.42
     brukes
    0.39
    Kit
    0.38
     سوز
    0.38
    rac
    0.38
    ナ
    0.38
    KT
    0.38
    Celebr
    0.38
    ശ
    0.38
    POSITIVE LOGITS
     Gray
    0.44
     GRAY
    0.42
     Grey
    0.42
     grey
    0.39
    pathTemplates
    0.38
    灰色
    0.38
     gray
    0.38
    灰
    0.38
    ម្
    0.38
    ipid
    0.38
    Activations Density 0.001%

    No Known Activations