© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31785
    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_40_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
     Sare
    0.41
    相
    0.39
     ㄹ
    0.38
     зад
    0.37
    谜
    0.37
     TRO
    0.36
     gem
    0.36
    teg
    0.36
    agement
    0.36
     Premium
    0.36
    POSITIVE LOGITS
     ủy
    0.38
     ਮੁ
    0.38
     Rutgers
    0.37
     hypoxia
    0.36
    ruppen
    0.36
    ∗
    0.35
    滦
    0.35
    য়ো
    0.34
     tun
    0.34
    档案
    0.34
    Activations Density 0.000%

    No Known Activations