Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 261758
    Prev
    Next
    INDEX
    Explanations

    numbers and time

    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_10_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
    व्ह
    0.55
     Adhesive
    0.54
    <unused2028>
    0.53
    <unused1116>
    0.52
     Shipment
    0.52
    戤
    0.52
    <unused346>
    0.51
     Oxidation
    0.51
    䣼
    0.51
    ătate
    0.51
    POSITIVE LOGITS
     so
    0.48
    -
    0.46
     sci
    0.43
     Thursdays
    0.43
    😂😂
    0.43
    कर्मियों
    0.42
     senza
    0.41
     editions
    0.40
     festive
    0.40
     egg
    0.40
    Activations Density 0.001%

    No Known Activations