© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196960
    Prev
    Next
    INDEX
    Explanations

    calculation formulas

    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_27_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
     például
    0.46
     Particular
    0.40
     especific
    0.37
     particular
    0.36
     крупные
    0.36
    詔
    0.36
     συγκεκρι
    0.35
     exemplu
    0.35
     например
    0.35
     například
    0.34
    POSITIVE LOGITS
    শ্বাস
    0.35
    ="#"><
    0.33
    --)
    0.31
    이지만
    0.31
    겠지만
    0.30
    Neben
    0.30
     afterward
    0.30
    ättre
    0.30
    स्ताना
    0.30
    ?”
    0.29
    Activations Density 0.032%

    No Known Activations