© 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
    2. Gemma-3-27B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 213144
    Prev
    Next
    INDEX
    Explanations

    interstate commerce clause

    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_5_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
     ansch
    1.08
    ";
    1.06
    "};
    1.06
    ");
    1.04
     indiqu
    1.02
     използва
    0.98
     veröffent
    0.96
    ”;
    0.95
     és
    0.95
     predict
    0.93
    POSITIVE LOGITS
    ق
    1.49
     on
    1.34
    ه
    1.21
    de
    1.18
    ت
    1.18
    ات
    1.14
    لی
    1.13
    ה
    1.13
    可以
    1.10
    ان
    1.07
    Activations Density 0.000%

    No Known Activations