© 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. 7864
    Prev
    Next
    INDEX
    Explanations

    cannot provide medical advice

    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
    גיע
    0.43
    ყენ
    0.38
     επί
    0.38
    حية
    0.38
    ಗ್
    0.38
     dritten
    0.38
    రుపు
    0.37
    ".*:
    0.36
    ෂ්
    0.36
     :-)
    0.36
    POSITIVE LOGITS
     overseas
    0.36
    ভাগ
    0.35
    oneph
    0.34
     নির্ব
    0.34
     ‘
    0.33
    推荐
    0.33
    тила
    0.33
    세계
    0.33
    范围
    0.33
    疑惑
    0.32
    Activations Density 0.001%

    No Known Activations