© 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. 36546
    Prev
    Next
    INDEX
    Explanations

    pom

    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
     '*':
    0.38
     mì
    0.37
    сит
    0.36
     গা
    0.36
    STAR
    0.36
     Schach
    0.36
    ﺴ
    0.36
    ্যাম
    0.36
    Cxx
    0.35
     تعد
    0.35
    POSITIVE LOGITS
     pump
    1.14
     Pump
    1.06
    pump
    1.02
    Pump
    0.97
     pumping
    0.96
     पंप
    0.95
     pumps
    0.94
     Pumps
    0.87
     pumped
    0.86
    泵
    0.84
    Activations Density 0.000%

    No Known Activations