© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 197281
    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_9_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
    м
    0.55
     массив
    0.51
     கணி
    0.50
     površ
    0.49
    вода
    0.48
     décadas
    0.48
    ל
    0.48
     اسرائی
    0.47
     decenas
    0.47
    к
    0.46
    POSITIVE LOGITS
    Control
    0.46
    VP
    0.45
    वेत
    0.44
     راہ
    0.43
    Profile
    0.43
     Controle
    0.43
    Business
    0.42
    Table
    0.41
    </code>
    0.41
     Platform
    0.41
    Activations Density 0.000%

    No Known Activations