© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5938
    Prev
    Next
    INDEX
    Explanations

    import Foundation

    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
    まと
    2.05
    ために
    2.02
    ઠ
    1.90
    urity
    1.87
    न
    1.86
    𝘃
    1.85
    𝗱
    1.80
    नियर
    1.78
    पणे
    1.77
    ന
    1.76
    POSITIVE LOGITS
    <0x1C>
    2.64
    ol
    2.49
    ɳ
    2.48
     unattended
    2.34
    ал
    2.27
     Decree
    2.24
     cls
    2.21
     uproar
    2.16
     traitor
    2.13
     integrable
    2.12
    Activations Density 0.000%

    No Known Activations