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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 1086
    Prev
    Next
    INDEX
    Explanations

    message board question and answer sections, including greetings, questions, and formatting symbols.

    oai_token-act-pair · gemini-2.0-flash

    computer code

    np_token-act-pair-logits · gemini-2.0-flash

    Questions and answers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.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
    TagHelper
    -0.58
    BeginInit
    -0.58
     Mors
    -0.56
    herin
    -0.54
     vapours
    -0.53
    Talk
    -0.53
    aloo
    -0.50
     Krä
    -0.50
    talk
    -0.50
     convertView
    -0.50
    POSITIVE LOGITS
    AnimationsModule
    0.74
     lenker
    0.60
     Roskov
    0.59
    clearTimeout
    0.55
    Autoritní
    0.52
    andaan
    0.49
    Notae
    0.47
    Reviewer
    0.47
    WriteTagHelper
    0.46
     EdgeInsets
    0.46
    Activations Density 2.747%

    No Known Activations