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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 3611
    Prev
    Next
    INDEX
    Explanations

    words related to legal and bureaucratic documents and technical specifications

    oai_token-act-pair · gemini-2.0-flash

    instructions, options, examples

    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
     itſelf
    -1.00
     myſelf
    -0.91
    '},
    
    -0.91
    '):
    
    -0.85
     faſt
    -0.85
     Roskov
    -0.84
    :");
    
    -0.84
    ArgsConstructor
    -0.83
     [],
    
    -0.83
    ...");
    
    -0.82
    POSITIVE LOGITS
    :
    0.76
    ।
    0.59
    >
    0.58
    <strong>
    0.54
    makeText
    0.52
    ГЛА
    0.52
    ">
    0.52
    ?
    0.50
     pé
    0.50
    »
    0.49
    Activations Density 17.683%

    No Known Activations