© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214762
    Prev
    Next
    INDEX
    Explanations

    Louisiana

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    capital
    0.41
    Hi
    0.40
    Wie
    0.40
    New
    0.39
    Mid
    0.39
     Pieter
    0.38
     capital
    0.38
    晞
    0.38
    Ukraine
    0.37
    Assets
    0.37
    POSITIVE LOGITS
     Louisiana
    1.17
    Louisiana
    1.13
     louis
    0.89
     LOUIS
    0.80
     Louis
    0.79
     LSU
    0.74
    LOUIS
    0.74
     lou
    0.71
     LA
    0.71
     Luis
    0.70
    Activations Density 0.000%

    No Known Activations