© 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. 8456
    Prev
    Next
    INDEX
    Explanations

    a mix of German words, HTML markups, and hyphenated English words

    oai_token-act-pair · gemini-2.0-flash

    non-English snippets

    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
    TintMode
    -0.72
     AssemblyCulture
    -0.70
    AccessorTable
    -0.69
    躇
    -0.67
     Paglinawan
    -0.66
    IsMutable
    -0.62
    InvalidProtocol
    -0.59
    thâu
    -0.58
    MergeFrom
    -0.57
     utafitiHapana
    -0.56
    POSITIVE LOGITS
     يتيمه
    0.51
    duğu
    0.42
     vulgaires
    0.42
     edildi
    0.42
    InteropServices
    0.41
    ValueStyle
    0.40
    glen
    0.40
    Erreferentziak
    0.40
     edilir
    0.40
    ClientRect
    0.40
    Activations Density 0.130%

    No Known Activations