© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158732
    Prev
    Next
    INDEX
    Explanations

    Big Query Commerce

    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_2_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
    n
    1.94
    ن
    1.41
    la
    1.23
    I
    1.16
    ר
    1.14
    ন
    1.09
    ν
    1.09
    J
    1.00
     as
    0.99
     masterpiece
    0.98
    POSITIVE LOGITS
     are
    1.30
    2
    1.29
    та
    1.17
    ز
    1.12
     și
    1.08
    នៃការ
    1.08
    كبر
    1.05
    ك
    1.05
    are
    1.04
    ка
    1.02
    Activations Density 0.003%

    No Known Activations