© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 199044
    Prev
    Next
    INDEX
    Explanations

    be tricky

    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_9_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
    কে
    0.38
    FileUtils
    0.36
    ல்
    0.35
    ER
    0.35
    ль
    0.34
     Funcion
    0.32
    ﻳ
    0.32
    ORM
    0.32
    UR
    0.32
     будут
    0.32
    POSITIVE LOGITS
    ת
    0.66
    ע
    0.65
    س
    0.56
    ح
    0.50
    。
    0.48
    at
    0.47
    um
    0.46
    ع
    0.46
    us
    0.46
     for
    0.46
    Activations Density 0.047%

    No Known Activations