© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129055
    Prev
    Next
    INDEX
    Explanations

    poodle, Retriever

    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_6_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ل
    1.30
    عرف
    1.26
    ת
    1.20
    其他
    1.19
     attravers
    1.16
    f
    1.16
    ם
    1.13
    on
    1.12
    ה
    1.12
    ז
    1.11
    POSITIVE LOGITS
    <0x91>
    0.94
    ENT
    0.94
    AR
    0.90
    ot
    0.88
    는
    0.88
    ።
    0.88
    ut
    0.86
    AN
    0.86
     But
    0.86
     They
    0.86
    Activations Density 0.001%

    No Known Activations