© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 176326
    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_20_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
     玄
    0.45
    㽡
    0.43
     iced
    0.43
    encia
    0.42
     پسند
    0.42
     desp
    0.40
     demos
    0.40
    藐
    0.40
     пли
    0.40
     cristiana
    0.40
    POSITIVE LOGITS
     கூட்டு
    0.41
    チュラル
    0.40
     जाण
    0.40
    доров
    0.40
     संयुक्त
    0.39
    也在
    0.39
    കോ
    0.39
    leaves
    0.39
    地的
    0.38
    ਵੀ
    0.38
    Activations Density 0.000%

    No Known Activations