© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6115
    Prev
    Next
    INDEX
    Explanations

    academic language used in research papers

    oai_token-act-pair · gemini-2.0-flash

    Covering areas or lengths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     lenker
    -0.57
     eorum
    -0.50
    外部リンク
    -0.41
     viceversa
    -0.41
    mær
    -0.40
    Datuak
    -0.40
    ніципалі
    -0.39
    ighed
    -0.39
     appui
    -0.38
    nunca
    -0.38
    POSITIVE LOGITS
    <bos>
    0.79
    parsedMessage
    0.76
     Chwiliwch
    0.60
    }}],
    0.50
     the
    0.50
     resourceCulture
    0.49
    яз
    0.49
    fortawesome
    0.47
     millions
    0.47
    '}}
    0.47
    Activations Density 5.012%

    No Known Activations