© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 176820
    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_24_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
     corresponds
    0.42
    క్కు
    0.40
    レシピ
    0.38
    ஃ
    0.38
    コ
    0.37
    spre
    0.37
     =&
    0.35
     ہے
    0.35
     हि
    0.35
     が
    0.35
    POSITIVE LOGITS
     luyện
    0.42
     pavimento
    0.40
    ']."
    0.40
    녀
    0.39
     exercise
    0.39
     fă
    0.39
    ِيم
    0.38
     exercising
    0.37
     exercice
    0.37
     www
    0.37
    Activations Density 0.000%

    No Known Activations