© 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. 131430
    Prev
    Next
    INDEX
    Explanations

    taking turns

    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
    ↵↵
    0.95
     is
    0.87
    يران
    0.84
    йс
    0.82
    га
    0.81
    ە
    0.80
    ير
    0.80
    อม
    0.79
    ו
    0.79
     b
    0.78
    POSITIVE LOGITS
    ing
    1.09
    n
    1.08
     (
    0.97
    a
    0.93
    oh
    0.91
    edited
    0.91
    with
    0.89
    e
    0.89
    i
    0.88
    all
    0.86
    Activations Density 0.001%

    No Known Activations