© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31096
    Prev
    Next
    INDEX
    Explanations

    Yellow

    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_50_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
     ರೀತಿಯ
    0.41
     ର
    0.40
    वेदन
    0.39
     اكتب
    0.39
    usst
    0.39
    ode
    0.38
    cue
    0.38
     কয়
    0.37
     ø
    0.37
    inset
    0.37
    POSITIVE LOGITS
    Magn
    0.65
     Magn
    0.64
     Mag
    0.59
    magn
    0.57
     Magnus
    0.55
    MAG
    0.55
     magni
    0.55
     magn
    0.53
     MAG
    0.53
    Mag
    0.52
    Activations Density 0.000%

    No Known Activations