© 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. 206505
    Prev
    Next
    INDEX
    Explanations

    grams or abbreviations

    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
     künstler
    0.42
    Ფ
    0.42
    Buen
    0.40
    ্নে
    0.39
    Ontario
    0.39
    Joel
    0.39
    第壹百
    0.37
    Assured
    0.37
     Opinion
    0.37
     artistic
    0.37
    POSITIVE LOGITS
     своими
    0.40
    uku
    0.39
     اگه
    0.39
     (
    0.39
     eğer
    0.38
     bằng
    0.37
     বিগত
    0.37
    тельным
    0.36
     (£
    0.36
     રો
    0.36
    Activations Density 0.002%

    No Known Activations