© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77360
    Prev
    Next
    INDEX
    Explanations

    Georgia

    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_53_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
    levation
    0.40
    鐘
    0.38
    "]).
    0.38
    Ст
    0.38
    ."],
    0.38
    Slope
    0.37
    "]').
    0.37
     vá
    0.36
    Ва
    0.36
    ֲ
    0.36
    POSITIVE LOGITS
     Georgia
    0.46
     hast
    0.45
    ريط
    0.40
    edor
    0.40
     Georg
    0.40
    Georgia
    0.38
     rud
    0.38
     হার
    0.37
     luckily
    0.37
     ofrecen
    0.37
    Activations Density 0.001%

    No Known Activations