© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176394
    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_50_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
    𝐗
    0.39
    တင်း
    0.39
    萬元
    0.39
    დება
    0.38
     piace
    0.38
    леко
    0.37
     vuelto
    0.37
    scrire
    0.37
    機會
    0.37
    赋
    0.37
    POSITIVE LOGITS
     rencontres
    0.38
     Armenian
    0.38
     markers
    0.37
    रु
    0.37
     uploads
    0.37
     Markers
    0.37
     poroz
    0.37
     Turkish
    0.37
    кет
    0.36
     Eurasian
    0.36
    Activations Density 0.000%

    No Known Activations