© 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. 158040
    Prev
    Next
    INDEX
    Explanations

    technical code

    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
     Ingersoll
    0.44
    ukat
    0.41
    ゲー
    0.41
    兖
    0.41
    疫情防控
    0.40
     بن
    0.38
    RELL
    0.38
    పోయే
    0.38
     अजय
    0.38
    ਕੇ
    0.37
    POSITIVE LOGITS
    oodoo
    0.40
    는다
    0.38
    ולים
    0.38
    Red
    0.38
     mane
    0.37
    терна
    0.37
    णाचा
    0.37
    oooo
    0.37
    임
    0.37
     immobil
    0.37
    Activations Density 0.000%

    No Known Activations