© 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. 44017
    Prev
    Next
    INDEX
    Explanations

    causal relationships

    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
    る
    0.63
    은
    0.63
    was
    0.63
     was
    0.62
    نی
    0.62
     flaps
    0.61
    이었다
    0.61
    सी
    0.60
    ians
    0.60
    rically
    0.60
    POSITIVE LOGITS
    {},
    0.71
    ÓN
    0.68
     realice
    0.68
    {
    0.67
    س
    0.66
    <0x80>
    0.64
     realise
    0.63
    い
    0.63
    zonych
    0.60
     realize
    0.59
    Activations Density 0.001%

    No Known Activations