© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140539
    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_46_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
    create
    0.39
     magistrates
    0.39
    𝓼
    0.39
    ীন্দ্র
    0.38
    stream
    0.38
    ByURL
    0.38
    푐
    0.38
    stretch
    0.37
    Mae
    0.37
     Mauro
    0.37
    POSITIVE LOGITS
     exactly
    0.41
     differently
    0.40
     affirmatively
    0.40
     directly
    0.38
     clogged
    0.38
     Hagg
    0.38
     wirelessly
    0.38
    髭
    0.37
     Presidency
    0.37
     faithfully
    0.37
    Activations Density 0.000%

    No Known Activations