© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33660
    Prev
    Next
    INDEX
    Explanations

    pre

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Pri
    0.42
     amores
    0.41
    pri
    0.40
    찌
    0.40
     pri
    0.39
    stell
    0.38
     corpses
    0.38
    Sp
    0.38
     lom
    0.37
     Loeb
    0.37
    POSITIVE LOGITS
     пре
    0.96
    pre
    0.84
    Pre
    0.84
     pre
    0.83
     Pre
    0.82
     Preston
    0.80
    预
    0.78
     pré
    0.77
     PRE
    0.75
     Пре
    0.75
    Activations Density 0.002%

    No Known Activations