© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 60172
    Prev
    Next
    INDEX
    Explanations

    year or years

    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
    ation
    0.72
    ating
    0.63
     include
    0.61
    are
    0.60
     parrots
    0.59
     l
    0.59
     cellules
    0.59
     vines
    0.58
     F
    0.58
     articles
    0.58
    POSITIVE LOGITS
    ن
    0.76
    스로
    0.58
    Со
    0.54
    SEND
    0.54
    сон
    0.54
    的
    0.53
    LSTM
    0.52
    Gesch
    0.51
    为了
    0.50
    В
    0.50
    Activations Density 0.009%

    No Known Activations