Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12113
    Prev
    Next
    INDEX
    Explanations

    legal and statistical documents or mathematical expressions

    oai_token-act-pair · gemini-2.0-flash

    code and data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    AndEndTag
    -0.95
    protoimpl
    -0.89
    EndProject
    -0.88
    TagHelper
    -0.88
     tartalomajánló
    -0.87
    /**
    -0.87
     ProtoMessage
    -0.86
     CURIAM
    -0.86
     FetchType
    -0.83
    WebVitals
    -0.82
    POSITIVE LOGITS
    <caption>
    0.39
     w
    0.37
    片
    0.36
    pacs
    0.35
     W
    0.34
     
    0.34
    dear
    0.34
     Digital
    0.34
     V
    0.32
     Dr
    0.32
    Activations Density 2.053%

    No Known Activations