© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 86682
    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
     يس
    0.56
     acides
    0.50
     ممال
    0.46
     rougeâtres
    0.44
    ຜະລິດຕະພັນ
    0.43
     آنا
    0.43
    트는
    0.42
    ב
    0.42
     foncé
    0.41
     ок
    0.41
    POSITIVE LOGITS
    editing
    0.44
     surgical
    0.43
     learning
    0.42
     lounge
    0.41
     creative
    0.40
     geometric
    0.39
     business
    0.39
     virtual
    0.39
     luxury
    0.39
     multilingual
    0.38
    Activations Density 0.000%

    No Known Activations