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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 929
    Prev
    Next
    INDEX
    Explanations

    numerical data, especially years, page numbers, and journal/volume numbers

    oai_token-act-pair · gemini-2.0-flash

    scientific publications

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     unknownFields
    -0.61
    esModule
    -0.52
     bershka
    -0.45
     scin
    -0.43
     ~
    -0.43
    AntiForgeryToken
    -0.43
     beech
    -0.42
     biotite
    -0.42
    Hilsen
    -0.41
     bauer
    -0.41
    POSITIVE LOGITS
     pinulongan
    0.74
     defaultstate
    0.65
    AndEndTag
    0.64
    RepeatedField
    0.62
    脚注の使い方
    0.60
     становника
    0.58
    NOPQRST
    0.57
     surla
    0.57
    WaitGroup
    0.56
    Personendaten
    0.55
    Activations Density 8.676%

    No Known Activations