© 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
    2. Gemma-3-27B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 48526
    Prev
    Next
    INDEX
    Explanations

    code sections

    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_10_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
    -
    0.53
    :
    0.52
     centralized
    0.52
    تان
    0.50
     futura
    0.48
     abstracted
    0.47
     sectional
    0.47
     idiopathic
    0.47
     artificial
    0.46
     exchanger
    0.46
    POSITIVE LOGITS
    N
    0.84
    H
    0.80
    W
    0.76
    is
    0.73
    from
    0.70
    on
    0.69
    an
    0.67
    G
    0.66
    X
    0.66
    R
    0.64
    Activations Density 0.007%

    No Known Activations