© 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. 176103
    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
     Bering
    0.39
     Wong
    0.37
    gren
    0.36
    ریم
    0.36
    )&=
    0.36
    ninger
    0.35
     fir
    0.35
     installer
    0.35
    鐲
    0.35
    <0xA9>
    0.34
    POSITIVE LOGITS
     პრო
    0.42
    Col
    0.40
     Gente
    0.40
     Ultr
    0.39
     Día
    0.39
     अल्ट्रा
    0.39
    吺
    0.39
     Hòa
    0.38
    üllt
    0.38
    夻
    0.38
    Activations Density 0.000%

    No Known Activations