© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 89830
    Prev
    Next
    INDEX
    Explanations

    huge, vastness

    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
    Not in Any Lists

    No Comments

    Negative Logits
     eight
    0.22
     tư
    0.20
     four
    0.19
     nine
    0.18
     six
    0.18
    '){
    0.18
     VIII
    0.17
     workbench
    0.17
    :'.
    0.17
     ').
    0.17
    POSITIVE LOGITS
    signal
    0.20
    Morris
    0.18
     வேக
    0.17
    لاحظ
    0.17
    સાર
    0.17
     automatique
    0.17
    zám
    0.16
    자동차
    0.16
    しかし
    0.16
    Hg
    0.15
    Activations Density 0.003%

    No Known Activations