© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33787
    Prev
    Next
    INDEX
    Explanations

    banking and financial services

    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_3_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
    ש
    1.02
    ة
    0.95
    ↵↵
    0.94
     has
    0.94
    ید
    0.89
    ской
    0.86
    の
    0.86
    ﺑ
    0.85
    че
    0.83
    ות
    0.82
    POSITIVE LOGITS
     It
    0.98
     If
    0.79
     They
    0.65
     This
    0.62
     There
    0.59
     berp
    0.58
    𢎞
    0.57
     Entry
    0.56
    彠
    0.56
    猞
    0.55
    Activations Density 0.003%

    No Known Activations