© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 147588
    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_18_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
     in
    0.61
    <0x80>
    0.55
    0
    0.50
    Tec
    0.49
     σε
    0.48
    o
    0.46
        
    0.44
    ın
    0.44
    teil
    0.43
    在
    0.43
    POSITIVE LOGITS
    აზ
    0.55
    ⌔
    0.53
     табу
    0.52
    ᚐ
    0.52
    𒉆
    0.52
     वोटों
    0.52
     formules
    0.51
     tangents
    0.51
     tumours
    0.50
    ೇನೆ
    0.49
    Activations Density 0.000%

    No Known Activations