© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3037
    Prev
    Next
    INDEX
    Explanations

    Weaviate

    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_5_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
     dailySales
    1.05
    hidupan
    0.98
     keySchedule
    0.97
     nihil
    0.97
    芎
    0.97
    <unused610>
    0.95
     scrollBody
    0.94
    嗒
    0.93
     xhrObj
    0.93
    vió
    0.93
    POSITIVE LOGITS
    ين
    1.00
    ic
    0.99
    ड
    0.95
    ise
    0.94
    م
    0.94
    ist
    0.93
    +
    0.91
    ية
    0.91
    ky
    0.90
    way
    0.90
    Activations Density 0.002%

    No Known Activations