© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14543
    Prev
    Next
    INDEX
    Explanations

    Safety, Election, Indian, FIA, Officer

    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
    ]})
    0.40
    تری
    0.35
    ('['
    0.34
    证券
    0.34
     zásob
    0.34
    )}')
    0.34
    颶
    0.34
    눴
    0.34
    ATE
    0.33
    쳤
    0.33
    POSITIVE LOGITS
     depende
    0.36
    ピソード
    0.35
    henga
    0.34
     Student
    0.34
     спорт
    0.33
    ssl
    0.33
     Tul
    0.33
    บค้น
    0.33
    ៤
    0.33
     Marsh
    0.33
    Activations Density 0.021%

    No Known Activations