© 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-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 129972
    Prev
    Next
    INDEX
    Explanations

    numbered lists and sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    %)$
    0.41
    ۱۳
    0.41
     انك
    0.40
    wage
    0.40
    <0xBC>
    0.39
     হয়ে
    0.38
    >',
    0.38
    Ꭷ
    0.37
     psik
    0.37
    PREC
    0.37
    POSITIVE LOGITS
     stored
    0.40
     replenished
    0.38
     Chip
    0.36
    áló
    0.36
     Ham
    0.36
    हरी
    0.36
    ющиеся
    0.36
     Funds
    0.35
     అందించ
    0.35
     today
    0.33
    Activations Density 0.002%

    No Known Activations