© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231014
    Prev
    Next
    INDEX
    Explanations

    fibers

    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_6_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
    ق
    1.25
    ми
    1.18
    is
    1.15
    ו
    1.02
    ра
    0.98
    зви
    0.94
    as
    0.91
    기
    0.89
    ши
    0.88
    ведите
    0.87
    POSITIVE LOGITS
     that
    1.21
    p
    1.16
    om
    1.13
     T
    1.09
     t
    1.09
     M
    1.09
     an
    1.08
     to
    1.07
    ken
    1.07
    kl
    1.07
    Activations Density 0.001%

    No Known Activations