© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35119
    Prev
    Next
    INDEX
    Explanations

    evening activities

    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_11_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
     జరుగు
    0.68
     Благо
    0.65
    Agregar
    0.64
    大
    0.64
    Во
    0.63
    Cuenta
    0.63
    вов
    0.61
    خود
    0.61
    Lorsque
    0.60
    Благо
    0.60
    POSITIVE LOGITS
    :
    0.83
     apa
    0.72
     ID
    0.67
     ML
    0.66
    }
    0.65
     DR
    0.63
     NT
    0.63
    y
    0.63
     LL
    0.63
     RA
    0.62
    Activations Density 0.003%

    No Known Activations