© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 159269
    Prev
    Next
    INDEX
    Explanations

    struct

    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
    d
    1.47
    Z
    1.34
    the
    1.33
    al
    1.27
    x
    1.23
     of
    1.22
    də
    1.16
    is
    1.13
    ت
    1.13
    c
    1.13
    POSITIVE LOGITS
    ре
    1.04
     Большая
    1.04
    린
    1.04
    зыва
    1.01
    они
    1.00
    い
    0.99
    िस
    0.98
    ים
    0.98
     tanta
    0.97
    籟
    0.95
    Activations Density 0.000%

    No Known Activations