© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5456
    Prev
    Next
    INDEX
    Explanations

    code with the word "index" in various circumstances, including array indexing, UI focus, and thread state

    oai_token-act-pair · gemini-2.0-flash

    index

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.11
    ↵↵
    -0.67
    '
    -0.65
    ’
    -0.59
    ↵
    -0.53
    ‘
    -0.52
    owohl
    -0.51
    <strong>
    -0.50
     of
    -0.46
     Franciscan
    -0.46
    POSITIVE LOGITS
     NSCoder
    1.12
    ElementException
    1.11
     kasarigan
    1.09
    LookAnd
    1.02
    extAlignment
    0.99
     &___
    0.96
    AddTagHelper
    0.95
    URLException
    0.92
     onOptions
    0.90
     transfieras
    0.88
    Activations Density 1.071%

    No Known Activations