© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7821
    Prev
    Next
    INDEX
    Explanations

    technical documents, especially patents and scientific papers

    oai_token-act-pair · gemini-2.0-flash

    technical writing

    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
    <em>
    -0.53
    ↵
    -0.50
    1
    -0.50
    The
    -0.49
    0
    -0.48
    3
    -0.47
    <strong>
    -0.47
    PR
    -0.46
    2
    -0.45
    Type
    -0.45
    POSITIVE LOGITS
    '},
    0.91
    )];
    0.85
     EnglishChoose
    0.85
     \\
    0.85
     BorderRadius
    0.84
     AssemblyVersion
    0.83
    \\
    0.83
     Theſe
    0.82
    fromnode
    0.81
     Roskov
    0.80
    Activations Density 29.676%

    No Known Activations