© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16119
    Prev
    Next
    INDEX
    Explanations

    descriptions of chemical compounds and their use

    oai_token-act-pair · gemini-2.0-flash

    Industrial resins and polymers

    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
     InputDecoration
    -0.79
     مرئيه
    -0.65
     chrétiens
    -0.65
    NewUrlParser
    -0.63
    хьтан
    -0.60
    GraphicsUnit
    -0.59
     chrétienne
    -0.59
    fitrión
    -0.59
     étoient
    -0.56
    はじめに
    -0.55
    POSITIVE LOGITS
     super
    0.62
     Super
    0.57
    cyd
    0.57
    super
    0.52
    Super
    0.52
     Aro
    0.50
     pol
    0.49
    kháu
    0.48
    SUPER
    0.48
     SUPER
    0.47
    Activations Density 1.585%

    No Known Activations