© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5810
    Prev
    Next
    INDEX
    Explanations

    birth control pills and combined medications

    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
    ostomy
    0.37
    昇
    0.37
    知道
    0.37
     Unavailable
    0.36
    ábado
    0.36
    㪇
    0.36
    LLB
    0.35
    ();//
    0.35
    奈川
    0.35
    ﮭ
    0.35
    POSITIVE LOGITS
     combinado
    0.41
     rendah
    0.39
     низ
    0.38
    합
    0.38
     Combined
    0.37
    হাম
    0.37
     Yas
    0.37
    combined
    0.37
    Combined
    0.36
     retin
    0.36
    Activations Density 0.020%

    No Known Activations