© 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. 89416
    Prev
    Next
    INDEX
    Explanations

    undivided attention

    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
    增长
    0.43
    研修
    0.41
    ｿ
    0.41
    รายงาน
    0.41
    ระหว่าง
    0.40
    time
    0.40
     trabajado
    0.40
     ش
    0.39
     Shakespeare
    0.39
     খাওয়
    0.38
    POSITIVE LOGITS
    cm
    0.59
     ການ
    0.54
    cex
    0.54
    ivg
    0.52
    ai
    0.51
    cus
    0.51
    ue
    0.50
     उल्लंघन
    0.50
    pcm
    0.50
    Bm
    0.50
    Activations Density 0.000%

    No Known Activations