© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93240
    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_60_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
     subordination
    0.45
    сных
    0.43
    ច
    0.43
     dreary
    0.42
     subsidi
    0.42
     amounts
    0.41
     работ
    0.41
     سە
    0.41
    ᒻ
    0.41
    ंधन
    0.40
    POSITIVE LOGITS
    Nella
    0.81
    Quando
    0.79
    Questo
    0.71
     della
    0.70
    Grazie
    0.70
    Questa
    0.69
     popolare
    0.68
     spiega
    0.67
    Secondo
    0.66
    Dopo
    0.66
    Activations Density 0.000%

    No Known Activations