© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 87391
    Prev
    Next
    INDEX
    Explanations

    cynical

    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_60_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
    𝑘
    0.56
    aks
    0.49
    ке
    0.47
    kc
    0.47
    nk
    0.47
    kers
    0.47
    kyo
    0.46
    kA
    0.46
     k
    0.44
    innest
    0.44
    POSITIVE LOGITS
     ángulo
    0.48
     origem
    0.46
     descrição
    0.45
     ângulo
    0.45
     soliton
    0.45
     origen
    0.44
     documentación
    0.44
     resort
    0.44
     naturaleza
    0.43
     natureza
    0.43
    Activations Density 0.000%

    No Known Activations