© 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. 176041
    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
    రూ
    0.42
    etal
    0.41
    obra
    0.39
    경상
    0.38
     ഊ
    0.38
    होम
    0.37
     குறு
    0.37
    etus
    0.36
    tal
    0.36
    ovým
    0.36
    POSITIVE LOGITS
     УК
    0.43
    㥽
    0.41
    UEN
    0.41
    kę
    0.38
     Circ
    0.37
    ር
    0.37
    刬
    0.37
     spleen
    0.37
    пин
    0.37
    чный
    0.37
    Activations Density 0.000%

    No Known Activations