© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8460
    Prev
    Next
    INDEX
    Explanations

    time related words

    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
    en
    2.64
     trae
    2.24
    ن
    2.15
     همچ
    2.14
    𝐂
    2.05
    
    2.01
    ɳ
    1.95
    𝐄
    1.89
     sust
    1.89
    aun
    1.88
    POSITIVE LOGITS
     ashore
    2.05
    arak
    2.05
    যদি
    2.03
    ting
    2.01
    ‚
    1.94
    ות
    1.93
    ylim
    1.92
    張
    1.87
    KAR
    1.87
    гал
    1.82
    Activations Density 0.031%

    No Known Activations