© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13698
    Prev
    Next
    INDEX
    Explanations

    commercial mortgage-backed securities

    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_15_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
    ⏤
    0.66
     Миха
    0.64
     дипло
    0.59
    ⎯
    0.58
     Александр
    0.57
    }}$,
    0.55
     Михаил
    0.55
     Количество
    0.55
     Assange
    0.55
     Викто
    0.55
    POSITIVE LOGITS
    /
    0.53
    夊
    0.53
     weak
    0.50
     variable
    0.48
     prefer
    0.48
    Keg
    0.47
     static
    0.46
     padding
    0.46
     vibrate
    0.46
     normal
    0.46
    Activations Density 0.001%

    No Known Activations