© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 47081
    Prev
    Next
    INDEX
    Explanations

    library names

    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_3_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
    s
    0.88
    (
    0.80
    ab
    0.68
    says
    0.68
    y
    0.68
    b
    0.66
    v
    0.66
    sorption
    0.65
    A
    0.64
    ve
    0.64
    POSITIVE LOGITS
     tkinter
    0.68
    オン
    0.64
    ه
    0.63
    ാ
    0.62
    ¹.
    0.62
    2
    0.61
     mediast
    0.61
    า
    0.61
    報道
    0.60
    他
    0.60
    Activations Density 0.001%

    No Known Activations