© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 135109
    Prev
    Next
    INDEX
    Explanations

    expansion of

    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_1_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
    s
    1.30
    r
    1.28
     was
    1.13
    n
    1.05
    <0x80>
    1.00
    ance
    1.00
    ere
    0.97
    هما
    0.96
    ut
    0.94
    b
    0.93
    POSITIVE LOGITS
    ו
    1.23
     hebat
    1.08
    و
    1.04
    ك
    0.98
     proteger
    0.94
     metod
    0.94
     rematch
    0.90
    ुरा
    0.87
     menyediakan
    0.82
    Д
    0.82
    Activations Density 0.000%

    No Known Activations