© 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. 253964
    Prev
    Next
    INDEX
    Explanations

    complex relations

    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
     मीटर
    0.38
    //@
    0.37
     אטאטורק
    0.37
     putem
    0.37
    ਲਾਂ
    0.37
    0.37
     ción
    0.37
    ​
    0.36
     uważ
    0.36
    اہد
    0.35
    POSITIVE LOGITS
     discontinuation
    0.41
     differentiator
    0.39
     correspondingly
    0.38
     simultaneously
    0.38
     reciproc
    0.38
    спользова
    0.37
     aproximadamente
    0.37
     interchangeably
    0.37
     simplification
    0.37
     approximately
    0.37
    Activations Density 0.007%

    No Known Activations