© 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. 195356
    Prev
    Next
    INDEX
    Explanations

    Neovim

    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
     部
    0.47
    OPS
    0.45
    部的
    0.42
    부에
    0.42
    OOP
    0.42
    veloc
    0.41
    olin
    0.41
    부는
    0.41
    क्तिक
    0.41
    uze
    0.40
    POSITIVE LOGITS
    히
    0.45
    숭
    0.43
     peine
    0.37
    seekg
    0.37
     switchTo
    0.36
    ﺟ
    0.35
    Alexander
    0.35
     Ev
    0.35
     Yur
    0.35
     нена
    0.35
    Activations Density 0.002%

    No Known Activations