© 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. 851
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of interactions of compounds and processes or things that are generally factual

    oai_token-act-pair · gemini-2.0-flash

    Materials and their properties

    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
     متعلقه
    -0.77
     незавершена
    -0.74
     EconPapers
    -0.72
    jface
    -0.66
     accessibility
    -0.63
    inigte
    -0.62
    Portale
    -0.61
    izability
    -0.61
     accesibles
    -0.60
     Taktlose
    -0.60
    POSITIVE LOGITS
     descri
    0.57
     pres
    0.54
     der
    0.52
     sel
    0.52
     tra
    0.52
     sal
    0.51
     defin
    0.50
     view
    0.49
     inser
    0.49
     repres
    0.48
    Activations Density 4.461%

    No Known Activations