© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 81076
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    aries
    0.46
    hae
    0.40
    chers
    0.40
    pf
    0.39
    ares
    0.39
    achery
    0.39
    ፊ
    0.38
    LIGHT
    0.38
    gh
    0.37
     productions
    0.37
    POSITIVE LOGITS
    开源
    0.42
    ैनल
    0.42
    embangunan
    0.41
     एंटीऑ
    0.40
    胧
    0.39
    tDBOutput
    0.38
    gulpfile
    0.38
    􀂾
    0.38
     मॉडल
    0.37
     menjel
    0.37
    Activations Density 0.000%

    No Known Activations