© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42090
    Prev
    Next
    INDEX
    Explanations

    word beginnings like 'ra', 're', 'ba', 'la', 'ca'

    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
    t
    1.13
    т
    0.66
     absol
    0.65
    s
    0.65
    tki
    0.64
    tų
    0.64
    tte
    0.64
    ζει
    0.63
    tku
    0.63
     on
    0.62
    POSITIVE LOGITS
    ة
    0.76
    的花
    0.74
    的确
    0.72
    V
    0.71
    的海
    0.71
    的价格
    0.71
    的時間
    0.71
    的样子
    0.70
    的名字
    0.70
    的身
    0.70
    Activations Density 0.001%

    No Known Activations