© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88366
    Prev
    Next
    INDEX
    Explanations

    Administration, Education, Wars, Press

    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_3_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
    氇
    0.72
    supportsFocus
    0.71
    stdout
    0.69
    gamb
    0.66
    甴
    0.63
     андроид
    0.61
     தொடர்பாக
    0.60
     determinante
    0.60
    glichen
    0.60
    '};
    0.59
    POSITIVE LOGITS
    ل
    1.30
    л
    1.10
    ल
    0.86
    ש
    0.84
    ল
    0.82
    ר
    0.82
    ล
    0.81
    し
    0.80
    त
    0.80
    ت
    0.77
    Activations Density 0.004%

    No Known Activations