© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 4962
    Prev
    Next
    INDEX
    Explanations

    the string "pur"

    oai_token-act-pair · gemini-2.0-flash

    words related to "pur."

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

    pur

    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
    expandindo
    -0.93
     againſt
    -0.57
     deſt
    -0.56
     autorité
    -0.56
     malattie
    -0.54
     kaarangay
    -0.53
     ویکی‌پدیا
    -0.53
     juſ
    -0.50
    الدراسه
    -0.50
     africains
    -0.50
    POSITIVE LOGITS
    posed
    0.55
    "?>
    0.53
    triangleq
    0.50
     poses
    0.49
    poses
    0.48
     pose
    0.48
    posing
    0.45
     lief
    0.44
    Filmographie
    0.44
    hase
    0.44
    Activations Density 0.529%

    No Known Activations