© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 6737
    Prev
    Next
    INDEX
    Explanations

    .

    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_44_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
     JI
    0.45
     ji
    0.42
    
    0.38
     kut
    0.38
    埶
    0.38
    空间
    0.38
     NSMutable
    0.37
     excise
    0.36
     grail
    0.36
     dru
    0.35
    POSITIVE LOGITS
    abody
    0.41
    STAR
    0.40
     Almost
    0.36
    jenje
    0.35
     Diamond
    0.35
    着用
    0.35
    etum
    0.35
     Debi
    0.35
    ]---
    0.34
     Kond
    0.34
    Activations Density 0.013%

    No Known Activations