© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 151954
    Prev
    Next
    INDEX
    Explanations

    Foundation of

    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_23_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
     Gore
    0.42
     Lincolnshire
    0.42
     calf
    0.39
     Suiza
    0.38
    />}/>
    0.38
     عنہ
    0.38
     这个
    0.38
     Scrum
    0.38
     Collagen
    0.37
    щие
    0.37
    POSITIVE LOGITS
    ThreadPool
    0.46
    真實
    0.44
    Pointing
    0.44
    薩
    0.43
    restaurant
    0.42
    মন্ত্রী
    0.42
    run
    0.41
    Kil
    0.40
    നി
    0.40
    3
    0.40
    Activations Density 0.017%

    No Known Activations