© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 155627
    Prev
    Next
    INDEX
    Explanations

    trust

    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
     Old
    0.61
    Old
    0.50
     OLD
    0.47
    老
    0.45
    वायरमेंट
    0.44
     বয়
    0.43
    বয়
    0.42
     OW
    0.41
     老
    0.39
     dren
    0.39
    POSITIVE LOGITS
     trust
    0.98
     Trust
    0.88
    trust
    0.83
    Trust
    0.81
     ट्रस्ट
    0.77
     Trusts
    0.66
     trusts
    0.65
     TRUST
    0.64
     дове
    0.60
    TRUST
    0.59
    Activations Density 0.003%

    No Known Activations