© 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. 108877
    Prev
    Next
    INDEX
    Explanations

    lux endings

    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
    า
    1.34
     have
    1.28
    い
    1.23
    اک
    1.07
     are
    0.98
     can
    0.98
     ک
    0.98
     as
    0.97
    ான்
    0.97
    ला
    0.96
    POSITIVE LOGITS
    s
    1.52
     in
    1.44
    在
    1.26
    ről
    1.19
    i
    1.16
    o
    1.16
    是真的
    1.16
    是
    1.10
    ۔
    1.05
    л
    1.01
    Activations Density 0.000%

    No Known Activations