© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11580
    Prev
    Next
    INDEX
    Explanations

    code snippets with lots of white space and special characters like //, (){}, and quotes

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    webElementXpaths
    -1.11
    Билгалдахарш
    -1.05
    SequentialGroup
    -1.02
    AndEndTag
    -0.96
     мәкал
    -0.93
    parsedMessage
    -0.88
     AssemblyCulture
    -0.88
    rungsseite
    -0.86
    XmlAccessType
    -0.85
    TagMode
    -0.83
    POSITIVE LOGITS
                                   
    0.58
     espir
    0.56
     seyn
    0.55
     bianchi
    0.53
    ________________
    0.53
     marseille
    0.53
     femei
    0.53
     dimo
    0.52
     étoit
    0.52
     teşekkür
    0.52
    Activations Density 6.540%

    No Known Activations