© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196717
    Prev
    Next
    INDEX
    Explanations

    Old Testament names

    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_27_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
    Host
    0.29
    🇹
    0.27
    ሕ
    0.25
    暢
    0.25
     сі
    0.25
     Dx
    0.25
    Compliance
    0.25
     ले
    0.25
    host
    0.24
     씨
    0.24
    POSITIVE LOGITS
    писа
    0.30
    trashButton
    0.30
    émique
    0.29
     junto
    0.28
    amerika
    0.28
    myer
    0.28
     glomer
    0.28
    ঙে
    0.28
    asciiPanel
    0.27
     ছন্দ
    0.27
    Activations Density 0.000%

    No Known Activations