© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58501
    Prev
    Next
    INDEX
    Explanations

    Right

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     righteous
    1.62
     righteousness
    1.33
    righteous
    1.23
     Dharma
    1.20
     dharma
    1.15
     dharm
    0.87
    义
    0.85
    義
    0.80
    ธรรม
    0.74
    harma
    0.70
    POSITIVE LOGITS
     Right
    1.03
    Right
    0.74
     Left
    0.51
     RIGHT
    0.48
     నీ
    0.47
     अध
    0.44
     의
    0.41
    тные
    0.39
     ನೀ
    0.38
     ধার
    0.38
    Activations Density 0.014%

    No Known Activations