© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 152127
    Prev
    Next
    INDEX
    Explanations

    numbers or digits

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ej
    0.52
    aub
    0.50
    eil
    0.48
    eed
    0.44
    ei
    0.43
    ofer
    0.43
    e
    0.42
    ein
    0.42
    rated
    0.42
    eaa
    0.42
    POSITIVE LOGITS
    1
    0.50
     eleven
    0.47
     Eleven
    0.46
     about
    0.45
     Thirteen
    0.45
     nine
    0.44
     Twelve
    0.44
     Forty
    0.43
    ^
    0.43
     One
    0.42
    Activations Density 0.000%

    No Known Activations