© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 15190
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to software updates, options, and compatibility

    oai_token-act-pair · gemini-2.0-flash

    Code and blog posts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )";
    
    -1.75
    "])
    
    -1.73
    ]";
    -1.71
    "]);
    
    -1.65
    "]));
    -1.64
     ]
    
    -1.59
    "],
    
    -1.55
    "]),
    -1.54
    "]
    
    -1.52
    ]");
    -1.50
    POSITIVE LOGITS
    </h2>
    0.90
    </h3>
    0.85
    Править
    0.58
    asantry
    0.54
     tí
    0.49
    uito
    0.49
    peth
    0.49
    </h1>
    0.48
    Edy
    0.48
    Edit
    0.48
    Activations Density 2.328%

    No Known Activations