© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 47169
    Prev
    Next
    INDEX
    Explanations

    Kurosawa, Kurosaki, Croesus

    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_3_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
    at
    0.63
     entice
    0.57
     প্রশ্নে
    0.52
    ᱔
    0.52
     সেরা
    0.52
     нуля
    0.52
    ﻊ
    0.51
    ᱘
    0.51
    osz
    0.51
    ISTS
    0.50
    POSITIVE LOGITS
    T
    0.98
    س
    0.87
    D
    0.80
    N
    0.78
    s
    0.77
    S
    0.76
     of
    0.74
    K
    0.74
    G
    0.72
    ש
    0.71
    Activations Density 0.007%

    No Known Activations