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. 7-GEMMASCOPE-TRANSCODER-16K
    4. 7082
    Prev
    Next
    INDEX
    Explanations

    proper nouns and words related to software and databases, potentially identifying named entities or specific technical terms.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    awtextra
    -0.91
     صوتيه
    -0.88
     فريبيس
    -0.86
    LookAnd
    -0.82
    +#+#
    -0.81
    ViewFeatures
    -0.73
    DockStyle
    -0.71
    AccessorTable
    -0.71
    MigrationBuilder
    -0.71
    TagMode
    -0.69
    POSITIVE LOGITS
    Filmographie
    0.54
    marginHorizontal
    0.50
    '])){
    
    0.50
     hänen
    0.49
    lardır
    0.47
    <bos>
    0.47
    Források
    0.46
    łyn
    0.45
    @[+][
    0.44
    ētu
    0.44
    Activations Density 9.932%

    No Known Activations