© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46891
    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
    a
    0.69
    া
    0.67
    ↵
    0.60
    า
    0.59
    il
    0.58
     TECHNOLOGY
    0.57
    ા
    0.53
     technolog
    0.53
    ม
    0.53
     are
    0.52
    POSITIVE LOGITS
    ரை
    0.57
    汜
    0.55
    sized
    0.55
    вається
    0.54
    bilir
    0.53
    εις
    0.52
     আপনারা
    0.52
    လည်း
    0.52
    cami
    0.52
    ę
    0.51
    Activations Density 0.000%

    No Known Activations