© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 89379
    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_60_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
     抗
    0.54
     항
    0.48
     ز
    0.46
     กลุ่ม
    0.45
     형태
    0.44
     ମ
    0.43
     ant
    0.43
     Ull
    0.43
     Vell
    0.42
     इट्स
    0.42
    POSITIVE LOGITS
    ي
    0.95
    i
    0.90
    י
    0.82
    ে
    0.68
    ி
    0.60
    ი
    0.57
    יש
    0.52
    ಿ
    0.52
    ी
    0.52
    ી
    0.50
    Activations Density 0.000%

    No Known Activations