© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261057
    Prev
    Next
    INDEX
    Explanations

    CIELAB colorspaces

    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_5_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
    the
    1.43
    ta
    1.23
    o
    0.99
    de
    0.98
    f
    0.97
    ts
    0.96
    sk
    0.95
    ten
    0.94
    ti
    0.94
    den
    0.85
    POSITIVE LOGITS
     importe
    0.82
    说过
    0.82
    ت
    0.82
    고
    0.79
     trabalh
    0.79
     aumenta
    0.79
    т
    0.78
    ال
    0.77
     anunci
    0.76
    ’
    0.76
    Activations Density 0.000%

    No Known Activations