© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144712
    Prev
    Next
    INDEX
    Explanations

    eulogy and FJ key

    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
     \
    1.56
     I
    1.50
     and
    1.33
    ів
    1.33
     byla
    1.27
     cały
    1.23
     Հ
    1.18
    ু
    1.18
    ານ
    1.17
    ות
    1.16
    POSITIVE LOGITS
    for
    1.37
    the
    1.30
    та
    1.25
    of
    1.23
    in
    1.20
    است
    1.20
    ulation
    1.18
    ،
    1.17
    out
    1.16
    ک
    1.14
    Activations Density 0.001%

    No Known Activations