© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206859
    Prev
    Next
    INDEX
    Explanations

    Missouri"}, "Missouri (MO)"

    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_20_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
    ляє
    0.46
     foul
    0.45
    elesaikan
    0.45
     Tokyo
    0.44
     line
    0.44
     metropolitan
    0.44
    练
    0.44
     metro
    0.42
    ною
    0.42
    oload
    0.42
    POSITIVE LOGITS
    inskii
    0.46
     Ganz
    0.46
     সৈন্য
    0.45
     Schwartz
    0.43
     vendedor
    0.42
    }^{*}$.
    0.41
    venuto
    0.40
    čna
    0.40
     বিচ্ছিন্ন
    0.39
    シック
    0.39
    Activations Density 0.000%

    No Known Activations