© 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. 82007
    Prev
    Next
    INDEX
    Explanations

    CAS numbers, standards, or abbreviations

    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
    1.66
    0
    1.63
    ed
    1.50
    3
    1.34
    ad
    1.24
    ig
    1.22
    ra
    1.22
    ture
    1.21
    token
    1.20
    ار
    1.18
    POSITIVE LOGITS
    م
    1.97
    ب
    1.95
    تی
    1.72
    い
    1.63
    ш
    1.63
    т
    1.59
    н
    1.56
    й
    1.55
    مي
    1.54
    த
    1.53
    Activations Density 0.000%

    No Known Activations