© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4644
    Prev
    Next
    INDEX
    Explanations

    let's break

    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_39_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
     কৈ
    0.40
    بازی
    0.40
    avidin
    0.38
    󰡔
    0.38
     konular
    0.37
    枸
    0.37
     पुस्तकें
    0.37
     pcl
    0.37
     букмекердик
    0.37
    ปฏิบัติ
    0.37
    POSITIVE LOGITS
    まとめ
    0.38
    𝗨
    0.38
     CO
    0.38
    明確
    0.37
     Industrial
    0.36
    ag
    0.36
     plain
    0.35
     industrial
    0.35
     dent
    0.35
     reef
    0.35
    Activations Density 0.075%

    No Known Activations