© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13964
    Prev
    Next
    INDEX
    Explanations

    the word "side" and phrases containing the word "side"

    oai_token-act-pair · gemini-2.0-flash

    side

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     laiss
    -0.60
    IsPostBack
    -0.56
     industriels
    -0.55
     oiseaux
    -0.54
     vettoriale
    -0.53
     touristes
    -0.53
     énergé
    -0.52
     françaises
    -0.52
     humains
    -0.52
     commerciaux
    -0.52
    POSITIVE LOGITS
     CreateTagHelper
    0.72
    GraphicsUnit
    0.65
    ArgumentParser
    0.62
    XmlEnum
    0.61
     виправивши
    0.60
    ContentAlignment
    0.60
     EconPapers
    0.58
     препратки
    0.58
    Sucesor
    0.58
    addGap
    0.56
    Activations Density 1.727%

    No Known Activations