© 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. 4123
    Prev
    Next
    INDEX
    Explanations

    words related to weapons, battles, and warriors

    oai_token-act-pair · gemini-2.0-flash

    medieval battles and knights

    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
     Roskov
    -0.70
     kasarigan
    -0.66
    styleType
    -0.58
     Mooney
    -0.58
    principalTable
    -0.57
    setVerticalGroup
    -0.57
    createServer
    -0.57
    ghted
    -0.56
    enumi
    -0.55
    Халык
    -0.54
    POSITIVE LOGITS
    <bos>
    0.77
     martial
    0.57
     inoxid
    0.57
     swords
    0.56
     combate
    0.55
     sword
    0.55
    LabelTagHelper
    0.55
     karate
    0.54
     chivalry
    0.53
     knights
    0.52
    Activations Density 0.917%

    No Known Activations