© 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. 36641
    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
     diatomic
    0.39
     pericard
    0.33
    versus
    0.33
    琇
    0.33
     myogenic
    0.31
    setRequestHeader
    0.31
     मीट
    0.31
    蕌
    0.31
    仂
    0.30
     versus
    0.30
    POSITIVE LOGITS
     ደ
    0.38
     comparte
    0.37
     thánh
    0.35
     applicant
    0.34
    hok
    0.33
     부정
    0.33
    事业单位
    0.32
     विक्रे
    0.32
     ஒளி
    0.32
     hok
    0.32
    Activations Density 0.000%

    No Known Activations