© 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. 5490
    Prev
    Next
    INDEX
    Explanations

    code and programming terms likely from multiple languages

    oai_token-act-pair · gemini-2.0-flash

    quote related punctuations

    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
     the
    -1.15
     purpoſe
    -1.14
     himſelf
    -1.13
     Diſ
    -1.09
     ſeveral
    -1.04
     Majefty
    -1.03
     themſelves
    -1.02
    neſs
    -1.02
     Eſ
    -1.02
     Reſ
    -1.00
    POSITIVE LOGITS
    <bos>
    1.58
    ↵
    1.13
    ↵↵
    1.10
    '
    0.92
    。
    0.79
     nakalista
    0.78
    （
    0.75
    ？
    0.69
    ')))
    0.69
    ‘
    0.68
    Activations Density 13.110%

    No Known Activations