© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33600
    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
     generation
    0.41
     及
    0.38
     leaves
    0.38
     বলিয়াই
    0.38
     hardware
    0.38
     grit
    0.37
     ister
    0.37
     ab
    0.37
     furniture
    0.36
     Hum
    0.36
    POSITIVE LOGITS
    ählt
    0.41
    ුවේ
    0.40
    teman
    0.39
    katan
    0.39
    )>=
    0.38
    ວນ
    0.38
     atores
    0.38
    旺
    0.38
    äfte
    0.38
    aronne
    0.37
    Activations Density 0.000%

    No Known Activations