© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7225
    Prev
    Next
    INDEX
    Explanations

    URLs, file paths, and code snippets

    oai_token-act-pair · gemini-2.0-flash

    Filepaths and code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ();)
    -0.54
    $.
    -0.35
     Dân
    -0.33
     Обо
    -0.32
     Wea
    -0.31
     piss
    -0.30
     boil
    -0.29
       
    -0.29
     Magic
    -0.29
     Sonar
    -0.29
    POSITIVE LOGITS
    setViewportView
    0.79
    setVerticalGroup
    0.77
    ConstraintMaker
    0.73
    SuppressLint
    0.73
    mybatisplus
    0.72
    TagMode
    0.71
    Hentet
    0.69
    VersionUID
    0.68
    twimg
    0.68
    WriteTagHelper
    0.68
    Activations Density 33.953%

    No Known Activations