© 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. 213090
    Prev
    Next
    INDEX
    Explanations

    Disco Elysium

    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
     Ei
    0.44
    orada
    0.41
     tall
    0.39
    ทด
    0.38
    奀
    0.38
     ei
    0.37
     වී
    0.37
     तैयारी
    0.37
    ᓃ
    0.37
     gif
    0.37
    POSITIVE LOGITS
     zako
    0.38
    काब
    0.37
    🖒
    0.37
     अब्
    0.36
    みの
    0.36
    autop
    0.36
    Matthew
    0.36
     Mahmoud
    0.36
    Tone
    0.36
     Mayo
    0.36
    Activations Density 0.002%

    No Known Activations