© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9730
    Prev
    Next
    INDEX
    Explanations

    time of day

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    魃
    0.80
     noon
    0.75
    དང་
    0.74
     প্রোডাক্ট
    0.73
     Ș
    0.73
    <unused54>
    0.71
    ждении
    0.70
    ➚
    0.70
     принци
    0.69
    Пла
    0.69
    POSITIVE LOGITS
    ionic
    0.62
    损
    0.60
    xp
    0.58
     depth
    0.58
    最为
    0.57
    leaf
    0.57
    損傷
    0.57
    leet
    0.56
    IL
    0.54
    depth
    0.54
    Activations Density 0.015%

    No Known Activations