© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 47138
    Prev
    Next
    INDEX
    Explanations

    Ryzen 5

    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_13_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
     便利
    0.49
    யா
    0.49
    ଝ
    0.47
     городской
    0.45
    ジャー
    0.43
    琪
    0.43
     パーカー
    0.43
    ্
    0.43
    fileID
    0.43
     स्थिती
    0.43
    POSITIVE LOGITS
     Input
    0.46
    ind
    0.43
    Investment
    0.43
    },
    0.42
    Account
    0.42
     Redis
    0.42
    Ind
    0.41
     Investment
    0.41
            
    0.41
    Configuration
    0.40
    Activations Density 0.011%

    No Known Activations