© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6596
    Prev
    Next
    INDEX
    Explanations

    references to things relating to being on the top (e.g. highest, or top of a list)

    oai_token-act-pair · gemini-2.0-flash

    top

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     vulgaires
    -0.65
     kind
    -0.52
     pinulongan
    -0.50
    γον
    -0.49
    hdl
    -0.49
    
    -0.48
     demandent
    -0.47
    anskje
    -0.46
    ALTH
    -0.45
    cluso
    -0.45
    POSITIVE LOGITS
    AddHtmlAttribute
    0.71
    DoubleQuotes
    0.68
    errHandler
    0.61
    endpush
    0.57
    moja
    0.57
    #+#
    0.56
    istorante
    0.51
    KEYCODE
    0.50
    脚注の使い方
    0.49
     actionPerformed
    0.49
    Activations Density 0.656%

    No Known Activations