© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48915
    Prev
    Next
    INDEX
    Explanations

    annuities or life insurance

    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_31_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
     প্রাদেশিক
    0.23
     äuß
    0.19
     ogen
    0.18
     Landkreis
    0.18
    utuskan
    0.18
     deregulation
    0.18
    ሦ
    0.18
    gamma
    0.18
    LIOGRAPHY
    0.18
     fulfilled
    0.17
    POSITIVE LOGITS
    Tact
    0.21
    Cardiac
    0.20
    DBObject
    0.20
     cated
    0.20
     अतिक्रमण
    0.19
    Chemistry
    0.19
    寻
    0.19
     trast
    0.19
     القلب
    0.18
     अतिक
    0.18
    Activations Density 0.009%

    No Known Activations