© 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. 16152
    Prev
    Next
    INDEX
    Explanations

    words and word fragments in languages other than English, especially words with accents

    oai_token-act-pair · gemini-2.0-flash

    Foreign language fragments

    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
     continúas
    -0.61
    Bio
    -0.54
     Bio
    -0.54
    bio
    -0.53
     bio
    -0.52
    adine
    -0.51
    Dyna
    -0.51
    че
    -0.51
     desist
    -0.50
    Wnd
    -0.50
    POSITIVE LOGITS
     télécommande
    0.56
     négociations
    0.54
    ammans
    0.54
    Šaltiniai
    0.54
     réfrig
    0.52
    UnknownFieldSet
    0.52
    (;;)
    0.52
     delgada
    0.52
    ыгана
    0.52
     VizieR
    0.52
    Activations Density 1.598%

    No Known Activations