© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 215659
    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_31_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
     Monk
    0.38
     cil
    0.37
     differentiator
    0.36
     diversification
    0.36
    ೪
    0.36
     personales
    0.35
    Persona
    0.35
     personas
    0.34
    個人
    0.34
    Ups
    0.34
    POSITIVE LOGITS
    吹き
    0.55
     स्टडी
    0.44
     써
    0.43
    arlan
    0.43
    国の
    0.41
     зак
    0.39
     공부
    0.39
     เขียน
    0.39
     awk
    0.38
    ☏
    0.36
    Activations Density 0.000%

    No Known Activations