© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208656
    Prev
    Next
    INDEX
    Explanations

    cocoa labor, farmers, Oriental, beans

    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_20_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
     Corea
    0.41
    ヨン
    0.40
    u
    0.40
     Holland
    0.38
    åll
    0.38
     Stockholm
    0.37
     *
    0.37
     Smack
    0.37
     financ
    0.35
     coincid
    0.35
    POSITIVE LOGITS
     জাম
    0.39
    бір
    0.39
    DateTimePicker
    0.39
    項目
    0.38
    ங்களைக்
    0.38
     ପ୍ର
    0.38
     습
    0.38
     submission
    0.38
     ValueError
    0.37
     cắt
    0.37
    Activations Density 0.009%

    No Known Activations