© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 110017
    Prev
    Next
    INDEX
    Explanations

    persistence

    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_2_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
    é
    1.09
     divulg
    1.04
    ä
    1.03
    arı
    1.02
     coloc
    0.96
    ва
    0.95
     examin
    0.94
    ﺪ
    0.93
     hypothes
    0.92
    น
    0.92
    POSITIVE LOGITS
    _
    1.01
    Unser
    0.96
    "/"
    0.96
    LING
    0.94
    N
    0.93
    ő
    0.92
    "});
    0.91
    }">
    0.91
    т
    0.89
     tidligere
    0.88
    Activations Density 0.002%

    No Known Activations