© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57314
    Prev
    Next
    INDEX
    Explanations

    REIT

    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_59_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
    etragen
    0.41
    atthe
    0.40
    icrob
    0.39
    xpath
    0.37
    OfThe
    0.36
    ptor
    0.36
    Austria
    0.35
    ન્ટ
    0.35
     !='')
    0.35
    at
    0.35
    POSITIVE LOGITS
     IT
    0.41
    ложений
    0.39
     Eye
    0.39
    蔫
    0.39
     Cum
    0.38
     Rewards
    0.38
     Llam
    0.38
     Information
    0.38
     Redeem
    0.38
    贋
    0.38
    Activations Density 0.000%

    No Known Activations