© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37253
    Prev
    Next
    INDEX
    Explanations

    signal transduction pathways molecules

    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
     señales
    0.78
     चलकर
    0.72
    ام
    0.70
    entwicklung
    0.70
     signaler
    0.69
    티
    0.68
    ar
    0.68
    ان
    0.67
    <0xBE>
    0.65
     circulación
    0.65
    POSITIVE LOGITS
     of
    1.08
     in
    0.91
    ly
    0.86
    B
    0.79
     -
    0.77
     by
    0.77
     ob
    0.76
    ian
    0.75
     b
    0.73
    -
    0.70
    Activations Density 0.016%

    No Known Activations