© 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. 166788
    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
     FLEX
    0.41
     utilized
    0.39
     Villain
    0.39
    液
    0.38
     Boost
    0.38
     taxed
    0.38
     O
    0.38
     Graphic
    0.38
     villain
    0.37
     utilizes
    0.36
    POSITIVE LOGITS
    shirts
    0.40
     episcopal
    0.39
    fullpath
    0.39
    黟
    0.38
     മുഴ
    0.38
    fashion
    0.38
    හි
    0.37
    멤버
    0.36
     HHS
    0.36
     Epoxy
    0.36
    Activations Density 0.000%

    No Known Activations