© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86252
    Prev
    Next
    INDEX
    Explanations

    table data and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
    Guid
    0.40
    dui
    0.40
    ﻒ
    0.39
     ductility
    0.39
    preferably
    0.38
    最大の
    0.37
     burst
    0.37
     Wallpaper
    0.37
    শ
    0.36
     कशी
    0.35
    POSITIVE LOGITS
    েন্ড
    0.39
     Союз
    0.39
    )}_{\
    0.38
     cession
    0.38
    ුණ
    0.38
     بتساوي
    0.37
     caballo
    0.37
    හර
    0.36
    畯
    0.36
     ANOVA
    0.36
    Activations Density 0.002%

    No Known Activations