© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 8409
    Prev
    Next
    INDEX
    Explanations

    a mix of HTML code with words in Portuguese and Spanish

    oai_token-act-pair · gemini-2.0-flash

    code fragments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    AsUp
    -0.62
     "..\..\
    -0.60
    MessageOf
    -0.59
     "..\..\..\
    -0.58
    ISupport
    -0.58
    AnimationsModule
    -0.56
    loem
    -0.54
    EndProject
    -0.54
    localctx
    -0.54
    currentColor
    -0.53
    POSITIVE LOGITS
    "]);
    
    1.02
    ']);
    
    0.90
    "];
    
    0.88
    "]];
    0.88
    '],
    
    0.87
    )";
    
    0.87
    "]);
    0.86
    "])
    
    0.86
    ?')
    0.85
    :");
    
    0.84
    Activations Density 2.250%

    No Known Activations