© 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. 131832
    Prev
    Next
    INDEX
    Explanations

    names

    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
    letscher
    0.42
     ಕಟ್ಟ
    0.40
    èdes
    0.40
     Slick
    0.38
    书
    0.38
    ୪
    0.38
    दल
    0.37
    舀
    0.37
    တော့
    0.37
    planar
    0.36
    POSITIVE LOGITS
     Pas
    0.40
     Maxine
    0.40
     PAS
    0.39
     Hercules
    0.38
     Wap
    0.38
     Garr
    0.38
    Pascal
    0.38
     Tok
    0.38
     C
    0.37
     Пас
    0.37
    Activations Density 0.000%

    No Known Activations