© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43836
    Prev
    Next
    INDEX
    Explanations

    Michael Jordan, Michael Phelps, Microsoft Store

    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
    J
    0.83
    O
    0.76
    Z
    0.73
     a
    0.67
    N
    0.67
    H
    0.67
     وك
    0.66
    HM
    0.64
    F
    0.64
    OB
    0.64
    POSITIVE LOGITS
    h
    0.80
    ώ
    0.64
    t
    0.61
    یل
    0.59
    לת
    0.58
    ul
    0.57
    اں
    0.57
    hg
    0.56
    지
    0.55
    مون
    0.55
    Activations Density 0.001%

    No Known Activations