© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15611
    Prev
    Next
    INDEX
    Explanations

    parenthesis surrounding some characters, especially ones used in coding contexts

    oai_token-act-pair · gemini-2.0-flash

    (

    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
     itſelf
    -1.66
     Jefus
    -1.59
     Theſe
    -1.54
     myſelf
    -1.54
     Efq
    -1.52
    ^(@)
    -1.50
    ſelves
    -1.49
     himſelf
    -1.48
    ſelf
    -1.48
     purpoſe
    -1.46
    POSITIVE LOGITS
    (
    1.33
    ↵↵
    1.32
    ((
    1.21
    ↵
    1.21
    '
    1.01
    (((
    0.97
     (
    0.95
     ((
    0.94
     
    0.91
    <strong>
    0.90
    Activations Density 0.506%

    No Known Activations