© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 3370
    Prev
    Next
    INDEX
    Explanations

    mentions of "bed" to indicate the presence of a bed

    oai_token-act-pair · gemini-2.0-flash

    bed

    np_max-act · gemini-2.0-flash

    bed

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -0.79
    nt
    -0.72
    NT
    -0.61
    ize
    -0.58
     obje
    -0.57
    d
    -0.56
        
    -0.56
     tav
    -0.54
    n
    -0.53
    <unused63>
    -0.53
    POSITIVE LOGITS
    )");
    
    1.13
    "]);
    
    1.05
    ()");
    0.99
    '));
    
    0.98
    $")
    0.98
    ')));
    0.97
    ']);
    
    0.95
    ."));
    0.94
    "));
    
    0.94
     ]
    
    0.94
    Activations Density 1.107%

    No Known Activations