© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 178152
    Prev
    Next
    INDEX
    Explanations

    Asiatic

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    Pa
    0.49
    Ry
    0.46
     M
    0.43
    Performance
    0.42
    Adam
    0.39
    Dane
    0.39
    River
    0.39
    Tre
    0.38
    alamat
    0.38
    割り
    0.37
    POSITIVE LOGITS
     wood
    0.48
     WOOD
    0.46
    ஜி
    0.45
     Wood
    0.43
    waitKey
    0.42
     木
    0.42
     Woody
    0.42
    Wood
    0.41
    木
    0.40
     anxiously
    0.40
    Activations Density 0.017%

    No Known Activations