© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 99956
    Prev
    Next
    INDEX
    Explanations

    CFA analysis

    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_16_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
     Quando
    0.53
    when
    0.52
     Иногда
    0.51
    ím
    0.50
     Cuando
    0.50
    <code>
    0.49
    autor
    0.49
    ob
    0.49
     Before
    0.48
    rá
    0.48
    POSITIVE LOGITS
    лық
    0.62
    식회사
    0.53
    रू
    0.52
    ෘ
    0.48
    დე
    0.48
    زندگی
    0.47
    嵃
    0.47
    ゼ
    0.47
    Rug
    0.46
    Ops
    0.46
    Activations Density 0.002%

    No Known Activations