© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172465
    Prev
    Next
    INDEX
    Explanations

    numbers following specific numbers

    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_20_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
     –
    0.52
     (
    0.42
     -
    0.42
     —
    0.40
     soaked
    0.39
     |
    0.39
    every
    0.37
    すべての
    0.37
     all
    0.37
     //
    0.37
    POSITIVE LOGITS
    прочем
    0.46
     vedit
    0.43
     Traveling
    0.41
    Պ
    0.40
     ছাড়
    0.40
     පේශ
    0.40
    Су
    0.40
     Проци
    0.40
    经销
    0.40
     Depreciation
    0.39
    Activations Density 0.000%

    No Known Activations