© 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
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12821
    Prev
    Next
    INDEX
    Explanations

    the letters "CR" or "WR" appearing in code or data tables

    oai_token-act-pair · gemini-2.0-flash

    CR

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     cr
    -1.97
    CR
    -1.91
    cr
    -1.85
     CR
    -1.82
     Cr
    -1.77
    Cr
    -1.77
    cra
    -1.22
    cri
    -1.07
    Cra
    -1.06
    <bos>
    -0.97
    POSITIVE LOGITS
    newswire
    0.74
    出版年
    0.73
     Réponses
    0.66
    windowFixed
    0.65
     rhestr
    0.64
    tzmann
    0.62
    }],
    0.62
     corporativa
    0.61
    MemoryWarning
    0.60
    classnames
    0.60
    Activations Density 1.258%

    No Known Activations