© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1956
    Prev
    Next
    INDEX
    Explanations

    various syntax elements of computer code like parenthesis, quotation marks, and semi-colons

    oai_token-act-pair · gemini-2.0-flash

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    <bos>
    -0.80
     protoimpl
    -0.56
    ::_('
    -0.56
     "..\..\
    -0.54
    ện
    -0.53
    ogia
    -0.53
     ModelExpression
    -0.51
    opan
    -0.47
    vetti
    -0.47
     cuadros
    -0.46
    POSITIVE LOGITS
    saraba
    0.55
    ÚBL
    0.48
    elesaikan
    0.47
     reck
    0.47
     InputDecoration
    0.47
    ِّف
    0.46
     tabPage
    0.46
     pax
    0.46
     wikipagina
    0.45
    IUrlHelper
    0.44
    Activations Density 1.643%

    No Known Activations