© 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. 209154
    Prev
    Next
    INDEX
    Explanations

    fulfills potential

    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
    Negative Logits
     wrong
    0.59
     against
    0.50
    wrong
    0.49
     Against
    0.46
    Wrong
    0.45
    Against
    0.45
     left
    0.43
     AGAINST
    0.42
    左
    0.41
    against
    0.41
    POSITIVE LOGITS
     wonderful
    0.41
     fulfills
    0.40
     Due
    0.39
    subject
    0.38
    fulfill
    0.38
     Do
    0.38
     cumple
    0.38
     Expand
    0.38
     subject
    0.37
     fulfill
    0.37
    Activations Density 0.003%

    No Known Activations