© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 178784
    Prev
    Next
    INDEX
    Explanations

    Eugene

    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
    Atlas
    0.41
     Lạt
    0.40
     Quadro
    0.40
    稷
    0.39
    Nova
    0.39
    ித்த
    0.38
    opard
    0.38
     }{}_{\
    0.38
     Atlas
    0.37
    壇
    0.37
    POSITIVE LOGITS
     Eugene
    2.22
    Eugene
    2.17
    Eug
    2.00
     Eug
    1.99
     Eugen
    1.88
     Eugène
    1.80
     Eugenia
    1.56
     Евге
    1.53
     Eugenio
    1.52
     Евгений
    1.48
    Activations Density 0.000%

    No Known Activations