© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8665
    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_40_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
    mt
    0.36
    యే
    0.35
    斧
    0.35
    file
    0.34
     गेंदबाजी
    0.34
    cida
    0.34
     हथियार
    0.33
     Bundesliga
    0.33
    엘
    0.33
     Files
    0.33
    POSITIVE LOGITS
    theorem
    0.39
     sebelah
    0.38
    BeerItem
    0.36
     зла
    0.36
    ⑦
    0.36
     sétimo
    0.35
     Giveen
    0.35
     похађа
    0.35
    雎
    0.35
     thật
    0.34
    Activations Density 0.000%

    No Known Activations