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. 4-GEMMASCOPE-TRANSCODER-16K
    4. 7736
    Prev
    Next
    INDEX
    Explanations

    statements of agreement between people or studies

    oai_token-act-pair · gemini-2.0-flash

    agree

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     agree
    -2.36
     agreement
    -2.16
     agreed
    -2.14
     Agree
    -2.09
     agrees
    -2.09
     Agreement
    -2.06
     agreeing
    -2.05
    agree
    -1.95
    agreed
    -1.91
    Agreement
    -1.89
    POSITIVE LOGITS
    enumi
    0.73
    Viitteet
    0.66
    ::__
    0.60
     Lest
    0.59
    󠁢
    0.58
    MIDDLEWARE
    0.55
    ########.
    0.52
    onOptions
    0.51
    cas
    0.51
     Cry
    0.50
    Activations Density 3.308%

    No Known Activations