© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6189
    Prev
    Next
    INDEX
    Explanations

    a mix of legal, technical , and mathematical terms, and words related to finance or exclusion.

    oai_token-act-pair · gemini-2.0-flash

    tokens related to legal terminology and references

    np_token-act-pair-logits · gpt-4o-mini

    Legal/technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     كومونز
    -0.76
    ंदीखरीदारी
    -0.75
    ViewFeatures
    -0.71
    BeginContext
    -0.71
    CDCl
    -0.67
     <<<<<<<<<<<<<<
    -0.66
    ManagedBean
    -0.65
     nahilalakip
    -0.64
    جغرافيا
    -0.63
     StatefulWidget
    -0.61
    POSITIVE LOGITS
    StoreMessageInfo
    0.52
     péri
    0.40
    >>()
    0.39
     referência
    0.39
     perigo
    0.37
    port
    0.37
    編成
    0.36
     port
    0.36
    commodations
    0.36
    ніципа
    0.36
    Activations Density 2.136%

    No Known Activations