© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37965
    Prev
    Next
    INDEX
    Explanations

    allowed to

    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
    ompact
    0.53
    of
    0.53
     yu
    0.53
    γρά
    0.51
    дам
    0.50
     村
    0.50
    OF
    0.49
     н
    0.49
    mless
    0.49
    compact
    0.48
    POSITIVE LOGITS
    Привет
    0.74
    З
    0.69
    Х
    0.68
    Про
    0.66
    ся
    0.66
    Пре
    0.66
    Б
    0.65
    Ч
    0.64
    Три
    0.63
    Ве
    0.61
    Activations Density 0.001%

    No Known Activations