© 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
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 11565
    Prev
    Next
    INDEX
    Explanations

    headache or pain

    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_13_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
     been
    0.39
     ند
    0.39
    Saving
    0.38
     barrier
    0.37
    5
    0.37
    運営
    0.36
    operated
    0.36
     toppings
    0.36
    (
    0.36
    です
    0.36
    POSITIVE LOGITS
    n
    0.75
    u
    0.66
    r
    0.60
    il
    0.59
    l
    0.56
    watercolor
    0.54
     inconsc
    0.53
    ra
    0.51
    lo
    0.51
    x
    0.51
    Activations Density 0.003%

    No Known Activations