© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43737
    Prev
    Next
    INDEX
    Explanations

    break, stop, loss, haired, wavelength

    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_3_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
    ל
    0.77
    ے
    0.62
    ле
    0.61
    ِی
    0.59
    ו
    0.58
     হইয়৷
    0.54
    ्स
    0.54
    ీ
    0.54
    ının
    0.53
    ę
    0.53
    POSITIVE LOGITS
     مكان
    0.70
     Konz
    0.68
    il
    0.66
    အတွက်
    0.66
     ترك
    0.65
     Allemagne
    0.63
    Ꮰ
    0.63
     écoles
    0.63
     vhodné
    0.63
     hohe
    0.62
    Activations Density 0.013%

    No Known Activations