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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260228
    Prev
    Next
    INDEX
    Explanations

    growth and investment Opportunity

    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_22_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
     insurmountable
    0.40
     responsable
    0.39
     extrémités
    0.39
     trav
    0.36
    珹
    0.36
     uncertainties
    0.35
     Productos
    0.35
     सुपरहिट
    0.35
     poumon
    0.35
     nomencl
    0.34
    POSITIVE LOGITS
     सुद्धा
    0.38
    рования
    0.35
    чення
    0.35
     Ransom
    0.34
    ICLES
    0.34
     Deli
    0.34
    klärung
    0.33
     Caffeine
    0.33
    켓
    0.33
    瓒
    0.33
    Activations Density 0.000%

    No Known Activations