© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 30281
    Prev
    Next
    INDEX
    Explanations

    New Mexico

    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_10_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
     italiano
    0.79
     AcOH
    0.79
     esperanza
    0.77
    ing
    0.75
     lotta
    0.73
     engines
    0.71
     pilha
    0.71
     k
    0.71
     acquies
    0.71
     choque
    0.70
    POSITIVE LOGITS
    3
    0.74
    كي
    0.71
    و
    0.70
    0.66
    皮
    0.65
    gameObject
    0.64
     على
    0.64
    during
    0.64
     في
    0.63
     در
    0.63
    Activations Density 0.001%

    No Known Activations