© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13056
    Prev
    Next
    INDEX
    Explanations

    a mix of code snippets from different languages and non-English words or characters

    oai_token-act-pair · gemini-2.0-flash

    Foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     autorytatywna
    -0.99
    RegistryLite
    -0.85
     кӀ
    -0.82
    GEBURTSDATUM
    -0.82
    MigrationBuilder
    -0.80
    sizeCache
    -0.79
    rungsseite
    -0.78
    WithIOException
    -0.76
     referenties
    -0.73
    fjspx
    -0.72
    POSITIVE LOGITS
     محفوظة
    0.57
    extAlignment
    0.48
    󠁢
    0.43
    ogonal
    0.43
     deveria
    0.42
     giác
    0.42
     adipis
    0.42
    ASK
    0.41
     Manas
    0.41
    OCK
    0.40
    Activations Density 4.338%

    No Known Activations