© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51769
    Prev
    Next
    INDEX
    Explanations

    breastfeeding, milk, immunity, health

    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
     ©
    0.38
    Copyright
    0.38
     Copyright
    0.37
    offsetHeight
    0.36
    ニング
    0.36
    logger
    0.35
     घंटों
    0.35
    Intercept
    0.35
    奶
    0.34
    fters
    0.34
    POSITIVE LOGITS
     Ironman
    0.38
    鑼
    0.38
     bệnh
    0.37
     reprises
    0.37
    disease
    0.36
     maladie
    0.35
     Disease
    0.35
     Bouch
    0.35
     tempor
    0.35
     iron
    0.35
    Activations Density 0.001%

    No Known Activations