© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 196268
    Prev
    Next
    INDEX
    Explanations

    technical approach or function syntax

    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_26_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
     வணக்கம்
    0.38
    жение
    0.37
     Sent
    0.36
    嵐
    0.35
    mph
    0.35
     tolerant
    0.35
    innerHTML
    0.34
    сок
    0.34
    KeyboardMarkup
    0.34
     founders
    0.33
    POSITIVE LOGITS
    নির্দিষ্ট
    0.41
     ม
    0.39
    iftet
    0.39
     உரிய
    0.38
     ও
    0.38
    犾
    0.38
     Linen
    0.37
     व
    0.36
     gene
    0.36
    都不是
    0.36
    Activations Density 0.012%

    No Known Activations