© 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. 176472
    Prev
    Next
    INDEX
    Explanations

    loss of wages or data

    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
     indebted
    0.46
     परिमेय
    0.46
     सापेक्ष
    0.46
     ditampilkan
    0.45
     рациона
    0.45
     Jahrze
    0.43
    軛
    0.43
     выполнение
    0.42
     Princeton
    0.42
     добав
    0.42
    POSITIVE LOGITS
    Reporter
    0.51
     deliver
    0.47
    ង
    0.44
     roasted
    0.43
     roast
    0.42
    Recorder
    0.41
    oine
    0.41
    deliver
    0.40
    μοί
    0.40
     life
    0.39
    Activations Density 0.000%

    No Known Activations