© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 211497
    Prev
    Next
    INDEX
    Explanations

    specific topics

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
     ডেপু
    0.37
    শিকান্ত
    0.36
    equilib
    0.36
    ̥
    0.36
    ီး
    0.36
    requis
    0.35
     মন্ত্রিস
    0.35
    Ẳ
    0.34
    </ul>
    0.34
     மதிப்ப
    0.34
    POSITIVE LOGITS
    olom
    0.37
     volley
    0.37
    asak
    0.37
     Ny
    0.37
    vrd
    0.37
    茧
    0.36
     stun
    0.36
     माया
    0.36
    Maf
    0.36
    unittest
    0.36
    Activations Density 0.000%

    No Known Activations