© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36699
    Prev
    Next
    INDEX
    Explanations

    her + descriptive noun or action

    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_11_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
    ﺀ
    0.70
     ευ
    0.64
    יה
    0.62
    이었다
    0.62
     بود
    0.62
    of
    0.61
    ?...
    0.61
     सामील
    0.59
     жер
    0.59
    льній
    0.57
    POSITIVE LOGITS
    et
    0.70
    م
    0.63
    š
    0.60
    am
    0.58
    ↵
    0.57
    os
    0.56
     not
    0.55
     echoes
    0.54
    不僅
    0.54
    ન
    0.54
    Activations Density 0.040%

    No Known Activations