© 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. 124837
    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
     corporation
    0.38
    包人
    0.36
     lies
    0.36
    ভেল
    0.36
    窖
    0.35
    iquet
    0.35
     madeira
    0.35
     pensioner
    0.34
     gubern
    0.34
     governador
    0.34
    POSITIVE LOGITS
     ιστο
    0.43
    唱
    0.42
     sifat
    0.39
     Render
    0.37
    вніш
    0.37
     लै
    0.36
    history
    0.36
     चिंता
    0.36
     न्यूज़
    0.36
    ிக
    0.36
    Activations Density 0.000%

    No Known Activations