© 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. 33561
    Prev
    Next
    INDEX
    Explanations

    get paid

    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
    ↵
    0.83
    I
    0.73
    ную
    0.64
    T
    0.61
    have
    0.59
    きた
    0.59
    is
    0.59
    has
    0.58
    E
    0.58
    i
    0.57
    POSITIVE LOGITS
     by
    0.73
    ្សែ
    0.66
    知らない
    0.64
    вости
    0.63
    ről
    0.62
    lardan
    0.61
    ूबी
    0.60
     aswell
    0.60
    用心
    0.59
    ت
    0.59
    Activations Density 0.005%

    No Known Activations