© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 694
    Prev
    Next
    INDEX
    Explanations

    professionals like artist, director, designer

    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_40_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
    Moore
    0.38
     বিবাহ
    0.37
    thomas
    0.36
     faithful
    0.36
    ської
    0.36
    Thomas
    0.36
    tak
    0.35
    刄
    0.35
    חק
    0.35
    esome
    0.34
    POSITIVE LOGITS
    highest
    0.44
     tertinggi
    0.44
     highest
    0.42
     najwy
    0.41
    鸚
    0.40
     Highest
    0.39
     उच्चतम
    0.39
     hög
    0.39
     किन्तु
    0.38
    Highest
    0.37
    Activations Density 0.009%

    No Known Activations