© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78287
    Prev
    Next
    INDEX
    Explanations

    ctypes or c transformers

    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_0_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
    ني
    1.58
    ين
    1.38
    تي
    1.37
     einzelne
    1.35
    ת
    1.32
    ঙ্গি
    1.30
    也
    1.26
    كيد
    1.25
    SP
    1.23
    로
    1.23
    POSITIVE LOGITS
    t
    1.71
    ua
    1.35
    s
    1.31
    uk
    1.27
    um
    1.16
    िया
    1.16
    waves
    1.15
    mo
    1.13
    rate
    1.12
    propylene
    1.10
    Activations Density 0.000%

    No Known Activations