© 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. 91182
    Prev
    Next
    INDEX
    Explanations

    credit card, credit limit, credit history

    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
    یس
    0.94
     It
    0.89
     to
    0.89
    C
    0.79
    D
    0.78
    It
    0.75
    ES
    0.73
     But
    0.72
    ص
    0.72
    ET
    0.68
    POSITIVE LOGITS
    e
    0.88
    t
    0.83
    documented
    0.68
    er
    0.67
    ev
    0.64
    dicke
    0.63
     λεπ
    0.62
    tia
    0.61
    aire
    0.61
    st
    0.60
    Activations Density 0.001%

    No Known Activations