© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27834
    Prev
    Next
    INDEX
    Explanations

    UCR

    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_10_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
    ال
    0.53
    safe
    0.52
    c
    0.51
    وا
    0.50
    ع
    0.50
    summon
    0.49
    为了
    0.48
    چ
    0.48
    sound
    0.47
    当
    0.46
    POSITIVE LOGITS
     Yen
    0.53
     Veränder
    0.52
     getY
    0.50
     言っ
    0.49
     hö
    0.49
     божомол
    0.49
     gele
    0.48
     Holz
    0.48
     lia
    0.48
    ሞች
    0.48
    Activations Density 0.000%

    No Known Activations