© 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. 139350
    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
    DEPARTMENT
    0.43
     nhảy
    0.41
    템
    0.41
     товар
    0.40
     meningkatkan
    0.40
     রোববার
    0.40
    Noble
    0.39
    improve
    0.38
     alert
    0.38
    verter
    0.37
    POSITIVE LOGITS
     যাহ
    0.36
     Áng
    0.36
     $(<
    0.36
    neurs
    0.36
     Out
    0.36
    ুৎ
    0.35
    outof
    0.35
    楇
    0.35
    водится
    0.35
    tainable
    0.34
    Activations Density 0.000%

    No Known Activations