© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9141
    Prev
    Next
    INDEX
    Explanations

    words related to government, institutions, and legal processes

    oai_token-act-pair · gemini-2.0-flash

    people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Krone
    -0.53
     anions
    -0.52
     Oficial
    -0.52
    Ufficio
    -0.51
     Económica
    -0.49
     Médico
    -0.49
    WriteLiteral
    -0.48
     Paix
    -0.48
    fonds
    -0.48
     Infantil
    -0.47
    POSITIVE LOGITS
    <bos>
    1.13
     كومونز
    0.79
    bootstrapcdn
    0.78
    /**
    0.76
    MigrationBuilder
    0.69
    Personendaten
    0.65
    UrlResolution
    0.62
     ComVisible
    0.59
    IsContent
    0.58
    رشف
    0.58
    Activations Density 6.418%

    No Known Activations