© 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. 9045
    Prev
    Next
    INDEX
    Explanations

    single digit numbers preceded by a space

    oai_token-act-pair · gemini-2.0-flash

    Code/Categories

    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
    ,'
    -0.69
     Chwiliwch
    -0.62
     '
    -0.62
    ,"
    -0.59
    )];
    
    -0.57
    .'
    -0.56
     ویکی‌آمباردا
    -0.56
    ?'
    -0.55
    /'
    -0.54
    ]'
    -0.54
    POSITIVE LOGITS
    TabIndex
    0.59
    TagHelpers
    0.56
    ficamente
    0.54
    ecirc
    0.50
     AssemblyCompany
    0.47
    noinspection
    0.46
     craindre
    0.46
    
    0.45
     jspb
    0.45
     chi̍t
    0.45
    Activations Density 10.210%

    No Known Activations