© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201094
    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
     Grass
    0.42
    辭
    0.39
     искус
    0.39
    ствовали
    0.39
     inquiries
    0.37
     scarcely
    0.37
     inquire
    0.37
     inquiry
    0.36
    毕
    0.36
    вис
    0.35
    POSITIVE LOGITS
     lod
    0.60
    Lod
    0.57
    lod
    0.54
     LOD
    0.49
     Lod
    0.43
     MAGNET
    0.43
    marker
    0.42
     पैनल
    0.42
    intervals
    0.41
     markers
    0.41
    Activations Density 0.000%

    No Known Activations