© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11734
    Prev
    Next
    INDEX
    Explanations

    nouns related to people or groups of people that also relate to an official capacity depending on region.

    oai_token-act-pair · gemini-2.0-flash

    people and groups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ρή
    -0.55
     chrétien
    -0.52
    tioned
    -0.52
     hæ
    -0.50
     RSSSF
    -0.47
     Aprile
    -0.46
     đo
    -0.46
     menti
    -0.45
     Saltar
    -0.45
     Heav
    -0.44
    POSITIVE LOGITS
    ThroughAttribute
    0.98
     EconPapers
    0.94
     كومونز
    0.79
    Бахар
    0.70
    CloseOperation
    0.66
    requestCode
    0.65
    AutoField
    0.63
    @[+][
    0.62
    ViewImports
    0.60
    httphttps
    0.60
    Activations Density 0.311%

    No Known Activations