© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20593
    Prev
    Next
    INDEX
    Explanations

    web code

    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_56_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
    ↵
    1.02
    ="#"
    0.40
    ].”
    0.39
    /\/
    0.39
    ={()
    0.39
    Printf
    0.38
    \%).
    0.38
    》（
    0.37
    
    0.37
    ᵈ
    0.37
    POSITIVE LOGITS
    </h3>
    0.61
    </h4>
    0.48
    <start_of_image>
    0.43
    ");
    0.39
    </h1>
    0.39
    Mehr
    0.39
    "});
    0.38
    ҷи
    0.38
    </body>
    0.36
     Docsity
    0.35
    Activations Density 0.294%

    No Known Activations