© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51563
    Prev
    Next
    INDEX
    Explanations

    #include

    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_10_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
     quà
    0.61
    的游戏
    0.59
     IEquatable
    0.59
    foresaid
    0.56
     ऑफ़
    0.56
    <unused582>
    0.55
    <unused99>
    0.54
     ክፍ
    0.54
    jach
    0.53
    രുവന
    0.53
    POSITIVE LOGITS
    0
    0.95
    1
    0.81
    a
    0.78
    C
    0.66
    R
    0.63
    8
    0.63
    {
    0.62
    2
    0.61
    ="
    0.60
    <
    0.59
    Activations Density 0.004%

    No Known Activations