© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91131
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_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
    3
    0.59
    跶
    0.58
    指定
    0.57
    2
    0.52
    FFF
    0.49
    吓
    0.49
    뿐
    0.48
    时间
    0.48
    政治
    0.47
    4
    0.46
    POSITIVE LOGITS
    ,|\
    0.49
    рие
    0.48
    لی
    0.47
     Primavera
    0.47
     aldehyde
    0.47
    ॉ
    0.47
    cosine
    0.46
    ків
    0.46
     outdoor
    0.46
     impetus
    0.46
    Activations Density 0.000%

    No Known Activations