© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16110
    Prev
    Next
    INDEX
    Explanations

    stack traces, or references to the line number of a file, potentially related to Python packages

    oai_token-act-pair · gemini-2.0-flash

    line

    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
    )))
    -0.52
    逆に
    -0.51
     Black
    -0.51
    一方で
    -0.50
    <0xB1>
    -0.49
    서는
    -0.49
    منة
    -0.46
     }$
    -0.46
     Gra
    -0.46
    tka
    -0.46
    POSITIVE LOGITS
     كومونز
    0.86
    rrggbb
    0.82
    extAlignment
    0.74
    <bos>
    0.74
     smtplib
    0.73
     AttributeSet
    0.73
    XmlRootElement
    0.73
    BufferException
    0.71
     XMLHttpRequest
    0.71
    RectangleBorder
    0.70
    Activations Density 0.416%

    No Known Activations