© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215303
    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
    }$,
    0.38
     Akin
    0.38
    TL
    0.38
    ුරු
    0.37
    尻
    0.37
     umur
    0.36
     रेलवे
    0.36
    atina
    0.35
    azin
    0.35
    葭
    0.35
    POSITIVE LOGITS
     इच्छ
    0.42
     perm
    0.40
     hypert
    0.40
     ale
    0.39
     Kxg
    0.38
     Ale
    0.37
     LE
    0.37
    ought
    0.37
     Раз
    0.37
    Ale
    0.37
    Activations Density 0.000%

    No Known Activations