© 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. 7676
    Prev
    Next
    INDEX
    Explanations

    loan terms and conditions

    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
    ectable
    0.37
    
    0.37
    ริม
    0.36
    undas
    0.36
     bricks
    0.35
    óricos
    0.35
    🇱
    0.34
     кей
    0.34
     三
    0.34
     Separ
    0.34
    POSITIVE LOGITS
     terms
    0.46
     Terms
    0.44
    Loan
    0.44
     Loan
    0.43
     Term
    0.42
    terms
    0.42
    Terms
    0.40
     repay
    0.40
     borrowed
    0.40
     loan
    0.40
    Activations Density 0.075%

    No Known Activations