© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4222
    Prev
    Next
    INDEX
    Explanations

    words indicating the act of making something false or negating it

    oai_token-act-pair · gemini-2.0-flash

    refuting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    VersionUID
    -0.62
     HasFactory
    -0.55
     honourable
    -0.50
    clientY
    -0.47
    Tcl
    -0.47
    DockStyle
    -0.46
    keyCode
    -0.45
    }{*}{}
    -0.45
    usammen
    -0.43
    anthene
    -0.42
    POSITIVE LOGITS
    <bos>
    0.77
    +#+#
    0.76
    BeginInit
    0.70
    <?>>
    0.66
     Betten
    0.61
     المعيارى
    0.60
     ThemeData
    0.58
    ponses
    0.58
     bezeichneter
    0.58
     مشين
    0.57
    Activations Density 1.340%

    No Known Activations