© 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. 1453
    Prev
    Next
    INDEX
    Explanations

    words related to temperature, air and weather, and also French language

    oai_token-act-pair · gemini-2.0-flash

    air flow

    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
    HtmlAttribute
    -0.60
    kheim
    -0.59
     indépend
    -0.55
    tagHelperRunner
    -0.54
    WriteAttribute
    -0.51
     مشين
    -0.50
    argli
    -0.50
    addPreferredGap
    -0.50
     Winaray
    -0.50
    Jsp
    -0.49
    POSITIVE LOGITS
    PhysRevD
    0.66
     transférez
    0.66
    NewUrlParser
    0.65
     estimés
    0.57
     drafts
    0.56
     themſelves
    0.55
    MessageTagHelper
    0.54
    TagMode
    0.52
    Commentaires
    0.49
    ContentAsync
    0.49
    Activations Density 0.898%

    No Known Activations