© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40505
    Prev
    Next
    INDEX
    Explanations

    word fragments

    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_57_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
    chi
    0.49
    CHI
    0.47
    ch
    0.46
    చి
    0.42
    chic
    0.39
    ち
    0.39
    喬
    0.39
    低
    0.39
    chas
    0.38
    chir
    0.38
    POSITIVE LOGITS
    hões
    0.47
    ፌ
    0.46
    prin
    0.43
    heath
    0.43
    اش
    0.41
    hell
    0.41
    niego
    0.41
     augmented
    0.40
    heen
    0.40
     Hel
    0.39
    Activations Density 0.007%

    No Known Activations