© 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-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15499
    Prev
    Next
    INDEX
    Explanations

    the letter "s" followed by a non-whitespace character

    oai_token-act-pair · gemini-2.0-flash

    s

    np_max-act · gemini-2.0-flash

    ▁s

    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
     s
    -0.69
    .
    -0.64
    /***/
    -0.61
    ↵
    -0.61
     
    -0.60
    What
    -0.59
    1
    -0.59
    [
    -0.58
    ce
    -0.58
        
    -0.57
    POSITIVE LOGITS
    ='';
    1.03
    )");
    1.00
    )++;
    1.00
    $")
    1.00
    ")));
    0.99
    )».
    0.98
    -),
    0.96
    "]));
    0.96
    )');
    0.95
    )"),
    0.95
    Activations Density 0.494%

    No Known Activations