© 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
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8705
    Prev
    Next
    INDEX
    Explanations

    instances of direct comparison

    oai_token-act-pair · gemini-2.0-flash

    versus or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     "..\..\
    -0.67
    otropy
    -0.56
     CreateTagHelper
    -0.55
     "..\..\..\
    -0.54
     astray
    -0.51
    wards
    -0.51
    atoires
    -0.49
    ergies
    -0.48
     Ach
    -0.48
     Assignee
    -0.48
    POSITIVE LOGITS
    <bos>
    1.27
    fillType
    0.63
    BeginContext
    0.63
     surla
    0.62
    sizeCache
    0.60
    ParallelGroup
    0.60
    djangoproject
    0.60
    UserScript
    0.57
    ibatis
    0.56
    kháu
    0.54
    Activations Density 0.645%

    No Known Activations