© 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. 3-GEMMASCOPE-TRANSCODER-16K
    4. 7308
    Prev
    Next
    INDEX
    Explanations

    names of people (often with titles or initials)

    oai_token-act-pair · gemini-2.0-flash

    academic papers, names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     ExecuteAsync
    -1.13
    脚注の使い方
    -1.02
    httphttps
    -1.01
    sidemargin
    -0.94
     HasFactory
    -0.94
     invokingState
    -0.88
    RegressionTest
    -0.87
     AssemblyCulture
    -0.85
    expandindo
    -0.84
    didSet
    -0.83
    POSITIVE LOGITS
    <bos>
    0.90
    '))
    0.53
    '));
    0.48
    '");
    0.47
    tér
    0.47
    '));
    
    0.45
    "))
    0.45
    ")(
    0.45
    '),
    0.44
    ]").
    0.44
    Activations Density 2.908%

    No Known Activations