© 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. 159699
    Prev
    Next
    INDEX
    Explanations

    out of

    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
    ل
    1.77
    ル
    1.71
    ल
    1.66
    И
    1.66
    л
    1.64
    ט
    1.38
    İ
    1.38
     ו
    1.30
    У
    1.27
    அ
    1.27
    POSITIVE LOGITS
    o
    1.91
    a
    1.84
    s
    1.77
    y
    1.51
    at
    1.33
    ä
    1.31
    ا
    1.25
    i
    1.22
    ib
    1.20
    \
    1.18
    Activations Density 0.001%

    No Known Activations