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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 980
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to PCR and DNA sequencing

    oai_token-act-pair · gemini-2.0-flash

    Revision

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Revision
    -0.43
     v
    -0.42
     contener
    -0.42
     revision
    -0.40
     contiene
    -0.37
    Revision
    -0.36
     rendition
    -0.36
    ciech
    -0.35
     universite
    -0.35
     garg
    -0.35
    POSITIVE LOGITS
    ngdoc
    0.82
     Савезне
    0.80
     resourceCulture
    0.77
     مشارکت‌کنندگان
    0.76
    NUMX
    0.74
    ("")]
    
    0.73
    WriteLiteral
    0.73
    Cyfarwyddwr
    0.72
     <=",
    0.71
     snippetHide
    0.71
    Activations Density 48.918%

    No Known Activations