© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159598
    Prev
    Next
    INDEX
    Explanations

    d followed by 'o', 'a', 'e', 'i'

    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_2_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
    個
    0.86
    дет
    0.81
     is
    0.78
    지는
    0.77
    д
    0.76
    ство
    0.75
     Subway
    0.75
     predator
    0.75
    場合
    0.74
    道
    0.73
    POSITIVE LOGITS
    it
    1.45
    c
    1.25
    ה
    1.20
    at
    1.19
    ל
    1.13
    ur
    1.10
    ie
    1.10
    al
    1.09
    ak
    1.04
    il
    0.99
    Activations Density 0.007%

    No Known Activations