© 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. 3369
    Prev
    Next
    INDEX
    Explanations

    childbirth and pregnancy

    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
     Zend
    0.39
     turpentine
    0.36
    ivar
    0.36
     الزد
    0.36
    룽
    0.36
    Bankruptcy
    0.35
     bilj
    0.35
     borrowings
    0.35
    췄
    0.35
     updateUser
    0.35
    POSITIVE LOGITS
     ces
    0.80
     Caes
    0.79
     caes
    0.77
     Ces
    0.73
     delivery
    0.65
    Ces
    0.65
     induce
    0.59
     induced
    0.59
     inducing
    0.58
     trimester
    0.58
    Activations Density 0.035%

    No Known Activations