© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 145213
    Prev
    Next
    INDEX
    Explanations

    independent or independently

    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_18_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
    겨
    0.49
     klimat
    0.42
     luminance
    0.42
    링
    0.39
     apertures
    0.39
     ARRAY
    0.39
     আজকাল
    0.39
    ulents
    0.39
    Є
    0.39
    П
    0.38
    POSITIVE LOGITS
    tsprec
    0.43
    :”
    0.41
     rebound
    0.40
    Deposit
    0.40
    :*
    0.40
    ង់
    0.39
    ...”
    0.39
    <unused1074>
    0.39
    ┘
    0.39
    <unused1031>
    0.38
    Activations Density 0.003%

    No Known Activations