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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171260
    Prev
    Next
    INDEX
    Explanations

    cannot, will not, impossible, refrain

    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
     azot
    0.24
    “
    0.23
    Ii
    0.23
     (“
    0.23
     ＜
    0.22
    nemis
    0.22
    opy
    0.22
     코로나
    0.22
    തിരെ
    0.22
    definition
    0.22
    POSITIVE LOGITS
    র্ত
    0.25
     observer
    0.24
     تتم
    0.24
     intric
    0.23
    些
    0.23
    的事情
    0.22
    observer
    0.22
     душе
    0.21
    والي
    0.21
     dinners
    0.21
    Activations Density 0.001%

    No Known Activations