© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223130
    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_10_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
     are
    0.54
    0.48
    Of
    0.44
    Ah
    0.44
     f
    0.42
     govern
    0.42
     ol
    0.41
     COUNT
    0.41
     Proposed
    0.40
     ARE
    0.40
    POSITIVE LOGITS
    Ꮰ
    0.58
    кр
    0.54
    ático
    0.54
    clockwise
    0.53
     நடு
    0.53
     sétimo
    0.53
    anon
    0.52
     درجة
    0.52
    𒀊
    0.52
     अभ्यास
    0.52
    Activations Density 0.000%

    No Known Activations