© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 251104
    Prev
    Next
    INDEX
    Explanations

    due

    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_56_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
     כי
    0.36
    utage
    0.33
    </tbody>
    0.32
     விரும்ப
    0.32
    だって
    0.32
    ம்பிய
    0.32
    놨
    0.32
    姦
    0.32
     Bởi
    0.32
    처
    0.31
    POSITIVE LOGITS
     due
    4.16
     Due
    3.84
    Due
    3.80
    due
    3.78
     DUE
    3.31
     devido
    2.98
     debido
    2.88
     بسبب
    2.69
    由于
    2.58
    เนื่อง
    2.42
    Activations Density 0.002%

    No Known Activations