© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82453
    Prev
    Next
    INDEX
    Explanations

    Past tense and related phrases

    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_0_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
    i
    2.64
    n
    2.30
    o
    2.25
    ي
    1.95
    q
    1.89
    r
    1.88
    y
    1.84
    l
    1.84
    ne
    1.80
    v
    1.77
    POSITIVE LOGITS
    д
    1.46
    дку
    1.19
    スの
    1.18
    дят
    1.17
     exclu
    1.16
     It
    1.12
    ом
    1.04
    дная
    1.04
    ۰
    1.03
    дже
    1.02
    Activations Density 0.004%

    No Known Activations