© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28891
    Prev
    Next
    INDEX
    Explanations

    DayPass

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     hope
    0.42
    hope
    0.42
    Hope
    0.41
    希望
    0.39
     nadzie
    0.39
     esperanza
    0.38
    高等
    0.37
    :**
    0.36
    猛
    0.36
     orci
    0.36
    POSITIVE LOGITS
     artifacts
    0.40
    тол
    0.38
     god
    0.37
    ື
    0.37
     मोर
    0.37
     continent
    0.37
     заря
    0.37
    जगी
    0.36
    綃
    0.36
    ্লিকেশন
    0.35
    Activations Density 0.002%

    No Known Activations