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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8941
    Prev
    Next
    INDEX
    Explanations

    various definite and indefinite articles, prepositions, and pronouns

    oai_token-act-pair · gemini-2.0-flash

    Bodies of water

    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
     snippetHide
    -0.73
     صوتيه
    -0.72
    脚注の使い方
    -0.64
     AssemblyCulture
    -0.59
    Personendaten
    -0.58
     étroite
    -0.56
     <=",
    -0.56
     muualla
    -0.54
     igång
    -0.54
     réessayer
    -0.53
    POSITIVE LOGITS
     sea
    2.30
    sea
    1.83
     ocean
    1.80
     Sea
    1.72
    Sea
    1.63
    ocean
    1.51
     seas
    1.38
    海
    1.29
     oceans
    1.29
     SEA
    1.29
    Activations Density 3.495%

    No Known Activations