© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78249
    Prev
    Next
    INDEX
    Explanations

    1,000,000

    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_31_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
    चाल
    0.42
    uner
    0.41
    ૃ
    0.39
    LIK
    0.38
    дино
    0.37
    人和
    0.37
     좋아
    0.36
     রিলি
    0.36
    adika
    0.36
     humanities
    0.36
    POSITIVE LOGITS
    <0xDB>
    0.40
     arcu
    0.39
     exclaimed
    0.37
     coincides
    0.35
    വരെ
    0.35
     cout
    0.35
     elapsed
    0.34
     SIAM
    0.34
     intron
    0.34
    ﭑ
    0.34
    Activations Density 0.002%

    No Known Activations