© 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. 14834
    Prev
    Next
    INDEX
    Explanations

    mentions of the element silver, Ag

    oai_token-act-pair · gemini-2.0-flash

    Ag

    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
     Qu
    -0.50
     상세
    -0.50
    SetItem
    -0.48
     as
    -0.47
    tagHelper
    -0.46
    Underline
    -0.46
    tois
    -0.45
    simon
    -0.45
     OnInit
    -0.45
    aternal
    -0.44
    POSITIVE LOGITS
    phalt
    0.57
     circonst
    0.56
    GraphicsUnit
    0.55
    🏻‍♀️
    0.54
    دانشنامهٔ
    0.53
     contextLoads
    0.53
    zeitig
    0.51
    Geograf
    0.51
    ToAction
    0.51
     tartalomajánló
    0.51
    Activations Density 0.706%

    No Known Activations