© 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. 216668
    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
     BET
    0.37
    借り
    0.36
    guez
    0.35
     hài
    0.35
    𝙙
    0.35
    اع
    0.35
     đam
    0.35
     vt
    0.35
     pleated
    0.35
    दायक
    0.34
    POSITIVE LOGITS
     سٹ
    0.49
    ہد
    0.46
     ঔষধ
    0.41
    ľ
    0.41
     பார்த்த
    0.39
     Tru
    0.38
     Syracuse
    0.38
    ី
    0.38
    тека
    0.37
    Eur
    0.37
    Activations Density 0.000%

    No Known Activations