© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4438
    Prev
    Next
    INDEX
    Explanations

    words related to jeep or truck accessories, specifically steps

    oai_token-act-pair · gemini-2.0-flash

    terms related to trucks or pickups

    np_token-act-pair-logits · gpt-4o-mini

    cowboy/trucks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     دیکھیے
    -0.65
     Leung
    -0.60
    DllImport
    -0.60
    ValueStyle
    -0.60
    ciss
    -0.59
    apunov
    -0.59
     asiatique
    -0.59
    lgari
    -0.59
    تقاوى
    -0.57
     때문
    -0.57
    POSITIVE LOGITS
     cowboy
    0.66
     pickup
    0.66
    pickup
    0.59
     rodeo
    0.58
    牛仔
    0.56
     truck
    0.55
     Bull
    0.54
     bull
    0.54
    UseVisualStyle
    0.53
     Frontier
    0.53
    Activations Density 1.938%

    No Known Activations