© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39026
    Prev
    Next
    INDEX
    Explanations

    class, state, forces, conflict, behavior

    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
     weep
    0.57
     kinerja
    0.57
     Minggu
    0.56
    ж
    0.55
     clan
    0.53
     psychologically
    0.53
     Perspekt
    0.53
     estis
    0.53
    ujem
    0.53
     पहने
    0.53
    POSITIVE LOGITS
    ED
    0.56
    K
    0.54
    itte
    0.53
    ס
    0.52
    S
    0.51
    NEY
    0.50
    म
    0.50
    Z
    0.50
    Fd
    0.49
    EME
    0.49
    Activations Density 0.021%

    No Known Activations