© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131997
    Prev
    Next
    INDEX
    Explanations

    order of things

    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_1_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
    I
    1.77
    U
    1.51
    K
    1.44
    G
    1.41
    (
    1.38
    H
    1.32
    O
    1.24
    <0x80>
    1.21
    D
    1.21
    W
    1.21
    POSITIVE LOGITS
    ле
    1.05
    れ
    1.05
    нер
    1.04
     ORNL
    1.02
    ра
    1.01
    ла
    1.00
    ला
    1.00
     métallique
    0.99
     फुले
    0.98
     SLAs
    0.98
    Activations Density 0.002%

    No Known Activations