© 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
    2. Gemma-3-27B-IT
    3. 20-GEMMASCOPE-2-TRANSCODER-262K
    4. 173451
    Prev
    Next
    INDEX
    Explanations

    won't regret it

    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
    норий
    0.49
     monsoon
    0.43
     የሚያ
    0.41
     summer
    0.41
    нечно
    0.40
     continuation
    0.39
    monia
    0.39
    V
    0.39
    嶌
    0.39
    <0xB5>
    0.39
    POSITIVE LOGITS
    リカ
    0.42
    🖒
    0.41
    놁
    0.41
     atlet
    0.40
    👏👏
    0.39
     poca
    0.39
    👍
    0.39
     رج
    0.37
     কিলো
    0.37
     👍
    0.37
    Activations Density 0.000%

    No Known Activations