© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12312
    Prev
    Next
    INDEX
    Explanations

    mentions of places and locations whether or not they are historical or current

    oai_token-act-pair · gemini-2.0-flash

    site

    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
     site
    -2.70
     Site
    -2.48
    site
    -2.44
    Site
    -2.42
     sites
    -2.23
     Sites
    -2.11
     SITE
    -2.09
    sites
    -1.93
    SITE
    -1.92
    Sites
    -1.87
    POSITIVE LOGITS
    providedIn
    0.84
     Theſe
    0.77
     Efq
    0.75
     snippetHide
    0.74
    出版年
    0.74
     ―――――
    0.73
    #+#
    0.73
    ScopeManager
    0.72
    tagez
    0.72
     EconPapers
    0.70
    Activations Density 1.472%

    No Known Activations