© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125730
    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_37_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
     primary
    0.41
     longest
    0.39
    𝗅
    0.38
     chief
    0.37
    longest
    0.36
     contracting
    0.36
     largest
    0.36
     greatest
    0.36
     transverse
    0.36
    edict
    0.36
    POSITIVE LOGITS
    ✎
    0.46
     peur
    0.38
    정을
    0.37
     రాయ
    0.37
    熹
    0.37
     mengakses
    0.35
     希望
    0.35
    ぞれ
    0.34
     ।।
    0.34
     sobriety
    0.34
    Activations Density 0.000%

    No Known Activations