© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 198739
    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_27_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
     definisi
    0.43
    菀
    0.40
     definición
    0.39
     অঞ্চ
    0.38
    rizioni
    0.37
    definition
    0.36
    珑
    0.36
     ú
    0.36
    **.
    0.36
     użyt
    0.36
    POSITIVE LOGITS
     النهار
    0.37
    白天
    0.37
    寒
    0.37
     clear
    0.36
    going
    0.35
     novice
    0.35
    <0xC2>
    0.34
     هاکي
    0.34
     homeowners
    0.34
     adolescents
    0.34
    Activations Density 0.000%

    No Known Activations