© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40909
    Prev
    Next
    INDEX
    Explanations

    ethical decision-making

    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_3_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
    '
    1.09
    ’
    1.00
    м
    0.96
    t
    0.76
    ம்
    0.72
    ہ
    0.70
    り
    0.68
    ד
    0.68
    ш
    0.66
    ം
    0.66
    POSITIVE LOGITS
    u
    0.93
    r
    0.63
    ides
    0.63
     cardiaque
    0.62
     ребенок
    0.62
     monoclonal
    0.61
     sorti
    0.61
     beschrieben
    0.60
     در
    0.60
     conten
    0.58
    Activations Density 0.000%

    No Known Activations