© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144210
    Prev
    Next
    INDEX
    Explanations

    French 'en' sound

    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_0_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
    '
    2.17
    y
    1.98
    i
    1.74
    s
    1.63
    d
    1.56
    ot
    1.46
    l
    1.46
     L
    1.41
    aaa
    1.37
    g
    1.37
    POSITIVE LOGITS
    ма
    1.80
    리
    1.63
    こと
    1.55
    ری
    1.49
    زی
    1.48
    ک
    1.44
     are
    1.41
    ές
    1.41
    か
    1.41
    ことです
    1.40
    Activations Density 0.001%

    No Known Activations