© 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. 8317
    Prev
    Next
    INDEX
    Explanations

    time specification with colon

    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
    т
    3.27
     JOptionPane
    2.97
     hydroly
    2.38
    👏👏
    2.34
     unacceptable
    2.30
    printf
    2.29
     heatmap
    2.29
    น์
    2.28
    \,.
    2.25
     illet
    2.24
    POSITIVE LOGITS
    tenths
    3.13
     asalamualaikum
    2.78
    ია
    2.71
     tenths
    2.67
    жных
    2.54
    С
    2.47
    ง
    2.42
     unteren
    2.42
     moeda
    2.40
    icrobial
    2.36
    Activations Density 0.096%

    No Known Activations