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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 389
    Prev
    Next
    INDEX
    Explanations

    the word "search" in various contexts, including general searching and coding-related searching

    oai_token-act-pair · gemini-2.0-flash

    typing in a text box

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ardos
    -0.46
    Trọng
    -0.41
    arn
    -0.41
     diffe
    -0.38
     polygonal
    -0.38
    zka
    -0.37
     engineers
    -0.37
    вер
    -0.36
    mặt
    -0.35
    Sock
    -0.35
    POSITIVE LOGITS
     InputDecoration
    0.93
    WebVitals
    0.83
    \{\\
    0.78
     OFDb
    0.78
     '\\;'
    0.77
     surla
    0.77
    migrationBuilder
    0.76
    awtextra
    0.75
    ⓧ
    0.75
     Normdatei
    0.74
    Activations Density 0.884%

    No Known Activations