© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6290
    Prev
    Next
    INDEX
    Explanations

    terms signifying appearance, impression, or compilation

    oai_token-act-pair · gemini-2.0-flash

    storytelling and books

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     EconPapers
    -0.81
    脚注の使い方
    -0.77
     متعلقه
    -0.75
     ExecuteAsync
    -0.75
    ,:]
    -0.74
    }")
    -0.71
    ).
    -0.71
    ".
    -0.71
     ब्रेकडाउन
    -0.70
    )";
    -0.68
    POSITIVE LOGITS
    <bos>
    1.17
     vastaan
    0.61
     aikaa
    0.59
     mukana
    0.55
    '
    0.52
     vuoden
    0.48
     Holocene
    0.47
     impressão
    0.47
     Tiberius
    0.46
     escon
    0.46
    Activations Density 0.458%

    No Known Activations