© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5811
    Prev
    Next
    INDEX
    Explanations

    tax, income, food banks, transparent costs

    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
     اہمیت
    0.40
     tématu
    0.38
    importanza
    0.38
    坆
    0.38
     डॉल
    0.38
    タイプ
    0.37
    +}
    0.37
    сні
    0.37
     Sprint
    0.37
    ś
    0.37
    POSITIVE LOGITS
     cul
    0.48
     parting
    0.42
    бут
    0.40
     javax
    0.35
     structure
    0.35
    essages
    0.35
    க்கூ
    0.35
     fly
    0.34
    ophosphate
    0.34
    estrutura
    0.34
    Activations Density 0.037%

    No Known Activations