© 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. 203928
    Prev
    Next
    INDEX
    Explanations

    is/being across languages

    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
     đều
    0.81
     شوند
    0.77
     dürfen
    0.76
    都能
    0.73
    都
    0.71
    都可以
    0.71
     eivät
    0.71
    都要
    0.70
    都很
    0.68
     都
    0.66
    POSITIVE LOGITS
     wordt
    0.72
     है
    0.70
     zostanie
    0.69
     został
    0.68
     производится
    0.67
     ہے
    0.67
     ఉంది
    0.67
     ہے۔
    0.66
     применяется
    0.66
     βρίσκεται
    0.66
    Activations Density 0.000%

    No Known Activations