© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43797
    Prev
    Next
    INDEX
    Explanations

    first national debit

    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
     is
    0.85
    j
    0.82
    ;
    0.79
     a
    0.79
     C
    0.74
     in
    0.70
    h
    0.66
    u
    0.66
    sp
    0.63
     Y
    0.61
    POSITIVE LOGITS
    ת
    1.05
    ت
    0.81
    at
    0.75
    لية
    0.75
    т
    0.70
    اك
    0.69
    твы
    0.69
    াল
    0.68
    لة
    0.68
    <unused73>
    0.67
    Activations Density 0.005%

    No Known Activations