© 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. 1279
    Prev
    Next
    INDEX
    Explanations

    references to relationships, groups, and spending time together

    oai_token-act-pair · gemini-2.0-flash

    together/with

    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
    ClientSize
    -0.56
    jsxFileName
    -0.53
    +#+#
    -0.50
    parseFloat
    -0.46
    περ
    -0.46
     "..\..\
    -0.45
    сев
    -0.44
    évaluateur
    -0.44
    нак
    -0.44
     AssemblyCulture
    -0.44
    POSITIVE LOGITS
    sizeCache
    0.71
     AppDelegate
    0.68
    mybatisplus
    0.63
    amentals
    0.62
     समीक्षाएं
    0.62
    ronesia
    0.60
     referenties
    0.59
    Espèce
    0.58
    MessageTagHelper
    0.58
    AddHtmlAttribute
    0.57
    Activations Density 1.419%

    No Known Activations