© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219950
    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_31_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
     दैट
    0.44
     கிருஷ்
    0.43
     কর্
    0.40
     Crane
    0.39
    Crane
    0.39
    打开
    0.37
     ঈ
    0.37
     காற்று
    0.37
    пъл
    0.36
    ValMap
    0.36
    POSITIVE LOGITS
     obligación
    0.40
    ყ
    0.36
     गुम
    0.35
    purecounter
    0.34
    arant
    0.34
     Repar
    0.34
    合同
    0.34
     чисто
    0.34
     inflammatory
    0.33
     biodegradation
    0.33
    Activations Density 0.000%

    No Known Activations