© 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. 230154
    Prev
    Next
    INDEX
    Explanations

    guilds and craftsmanship

    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
    1
    1.20
    <0x0D>
    1.15
    ä
    1.09
    ı
    1.05
    ü
    0.93
    ----------------
    0.89
     It
    0.83
     hypothes
    0.83
    oc
    0.81
     synthes
    0.80
    POSITIVE LOGITS
     in
    1.15
    ي
    1.11
    ق
    1.09
    ب
    1.02
     في
    1.01
    قوم
    0.99
    ní
    0.98
    
    0.97
    ع
    0.92
    ために
    0.90
    Activations Density 0.000%

    No Known Activations