© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7037
    Prev
    Next
    INDEX
    Explanations

    ineficaz, inusual, innegable, incontrolable, inmutable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
    𝘭
    1.52
    થી
    1.50
    𝖗
    1.50
    hips
    1.48
    wavelength
    1.47
    wget
    1.46
    ible
    1.46
    latitude
    1.46
    wilderness
    1.45
    من
    1.42
    POSITIVE LOGITS
    д
    1.96
    들이
    1.54
    들
    1.52
     бывают
    1.52
     biologiques
    1.40
     destes
    1.38
     quirúrg
    1.38
     daños
    1.37
     مؤرشف
    1.36
    ı
    1.35
    Activations Density 0.001%

    No Known Activations