© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83092
    Prev
    Next
    INDEX
    Explanations

    NuGet, XE, Æthelstan

    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_0_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
    ad
    2.03
    f
    1.99
    ।
    1.89
    ي
    1.78
    a
    1.67
    i
    1.66
    ड
    1.58
    )।
    1.57
    ר
    1.52
    (
    1.51
    POSITIVE LOGITS
     to
    1.80
    ﻢ
    1.45
    с
    1.37
    س
    1.27
     on
    1.27
    ни
    1.23
    เป็น
    1.19
     toată
    1.19
    ﻦ
    1.16
    จะ
    1.16
    Activations Density 0.000%

    No Known Activations