© 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
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 59202
    Prev
    Next
    INDEX
    Explanations

    still, then

    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_11_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
    (
    0.71
     administrat
    0.63
    numberOf
    0.63
    '}
    0.62
    ']/
    0.61
    takes
    0.60
    (|\
    0.60
    '=
    0.59
    isible
    0.59
    一项
    0.59
    POSITIVE LOGITS
     Даже
    0.68
     colonized
    0.67
     emozioni
    0.63
     euph
    0.63
     utopian
    0.62
     loro
    0.61
     attacker
    0.61
     debajo
    0.61
     paradise
    0.60
     bandeja
    0.60
    Activations Density 0.002%

    No Known Activations