© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132244
    Prev
    Next
    INDEX
    Explanations

    di/de prefixes

    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_6_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
    r
    1.21
     I
    0.96
    ্তার
    0.95
    o
    0.94
     H
    0.93
     B
    0.88
    te
    0.85
    .$-
    0.82
    )-
    0.80
     K
    0.79
    POSITIVE LOGITS
    ع
    1.26
    ش
    1.25
    ي
    1.20
    ни
    1.16
    ם
    1.14
    marca
    1.05
    νο
    1.02
    شون
    1.01
    عا
    1.00
    ີ້
    0.98
    Activations Density 0.001%

    No Known Activations