© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66829
    Prev
    Next
    INDEX
    Explanations

    code and plotting keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_41_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
     Brant
    0.55
     Hald
    0.44
    Turkey
    0.44
     Norfolk
    0.43
    Wayne
    0.43
     convi
    0.42
    Norway
    0.41
    桓
    0.39
    Grand
    0.38
     Grand
    0.38
    POSITIVE LOGITS
     carton
    0.37
     باذن
    0.37
     Carton
    0.36
    เคลื่อน
    0.36
    そ
    0.36
    infrastructure
    0.36
    මැ
    0.34
     oč
    0.34
     Pacquiao
    0.34
    搶
    0.34
    Activations Density 0.013%

    No Known Activations