© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74906
    Prev
    Next
    INDEX
    Explanations

    weekly contexts

    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
     executed
    0.36
    
    0.36
    Election
    0.35
     exécut
    0.35
    േഷന്‍
    0.35
     चुनाव
    0.34
     ricevere
    0.34
     election
    0.34
    蠱
    0.34
     फेस्टिव
    0.34
    POSITIVE LOGITS
     ammonium
    0.40
     সাংবাদিকদের
    0.36
     पत्रकार
    0.36
     journalism
    0.35
     সাংবাদিক
    0.35
     जितेंद्र
    0.35
    じめ
    0.34
    Buyers
    0.34
     passionate
    0.33
     reel
    0.33
    Activations Density 0.002%

    No Known Activations