© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253928
    Prev
    Next
    INDEX
    Explanations

    forming parts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     d
    1.63
     د
    1.25
     д
    1.20
    <0x93>
    1.02
     द
    0.97
     ד
    0.97
    d
    0.94
    ด
    0.86
     D
    0.80
     damit
    0.79
    POSITIVE LOGITS
     part
    0.52
     Forming
    0.48
    部分
    0.45
     forming
    0.42
    part
    0.41
     تشکیل
    0.40
     phần
    0.39
     Teil
    0.39
     حصہ
    0.38
    部份
    0.38
    Activations Density 0.000%

    No Known Activations