© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75414
    Prev
    Next
    INDEX
    Explanations

    short-circuit protection

    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_31_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
    霜
    0.38
    ਰੀ
    0.37
    투자
    0.36
    segaretro
    0.36
     রেজা
    0.35
     Geschichten
    0.35
    Новости
    0.35
    Merry
    0.35
    кс
    0.34
    ленного
    0.34
    POSITIVE LOGITS
    開催
    0.43
    辣
    0.42
     Fever
    0.39
     Hug
    0.39
     Nigam
    0.39
    連結
    0.39
     ц
    0.38
     विभक्ति
    0.38
    determination
    0.37
    癮
    0.37
    Activations Density 0.020%

    No Known Activations