© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4091
    Prev
    Next
    INDEX
    Explanations

    legal consequences or penalties

    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_40_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
    ربعة
    0.43
     ВК
    0.40
    ﺣ
    0.40
     kroppen
    0.38
    RIOT
    0.38
     Serv
    0.38
    Robertson
    0.37
    膩
    0.37
     Robertson
    0.36
     Wechsler
    0.36
    POSITIVE LOGITS
     commanding
    0.48
     attempted
    0.43
     tried
    0.42
    指揮
    0.38
     lam
    0.37
    ([\
    0.37
    ocompat
    0.36
    दर्शिता
    0.36
    tried
    0.35
    小心
    0.35
    Activations Density 0.055%

    No Known Activations