© 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. 88446
    Prev
    Next
    INDEX
    Explanations

    simulated annealing

    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
    ta
    0.76
     U
    0.66
    1
    0.63
    ι
    0.62
    an
    0.61
    take
    0.60
    tR
    0.58
    ל
    0.58
    ί
    0.58
    tan
    0.56
    POSITIVE LOGITS
    of
    0.76
    。
    0.69
    ప్
    0.66
    für
    0.63
    apsingToolbar
    0.58
    etzten
    0.57
     ventes
    0.57
    жая
    0.57
     Fútbol
    0.56
    ਫ
    0.55
    Activations Density 0.000%

    No Known Activations