© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48595
    Prev
    Next
    INDEX
    Explanations

    the

    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_55_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
     battles
    0.51
    Winners
    0.44
     battle
    0.43
    battle
    0.42
     Winners
    0.42
     Battles
    0.42
     bets
    0.42
     chose
    0.41
    戰
    0.40
     scelte
    0.40
    POSITIVE LOGITS
     relative
    0.58
     relatif
    0.53
     Relative
    0.50
    Relative
    0.48
     relativo
    0.45
    相对
    0.45
     relativa
    0.43
    relative
    0.42
     relatives
    0.42
     OST
    0.41
    Activations Density 0.012%

    No Known Activations