© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14914
    Prev
    Next
    INDEX
    Explanations

    html/javascript/css code snippets containing the word 'const', especially in the context of software development, bootstrap containers, and button defaults

    oai_token-act-pair · gemini-2.0-flash

    container

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    Location
    -0.66
    <bos>
    -0.63
    TemporalType
    -0.59
     EdgeInsets
    -0.54
     Location
    -0.53
    Geplaatst
    -0.51
    centerTitle
    -0.49
     saying
    -0.48
     location
    -0.48
     ModelAndView
    -0.48
    POSITIVE LOGITS
    principalTable
    0.74
    EDEFAULT
    0.65
    barui
    0.65
    NUMX
    0.60
    latego
    0.59
    HasForeignKey
    0.59
    จึง
    0.57
    DeleteBehavior
    0.57
    WithMany
    0.57
    uties
    0.57
    Activations Density 0.476%

    No Known Activations