© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 482
    Prev
    Next
    INDEX
    Explanations

    a collection of disparate phrases that I can not summarize

    oai_token-act-pair · gemini-2.0-flash

    how and jokes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    Хьажоргаш
    -0.57
    perity
    -0.55
     CommonModule
    -0.53
    virt
    -0.51
    tisgarh
    -0.49
     Unbe
    -0.49
    حياته
    -0.49
    SOUNDBITE
    -0.47
     pect
    -0.47
    currentColor
    -0.47
    POSITIVE LOGITS
    InstrumentedTest
    0.60
     BoxDecoration
    0.59
    kloped
    0.55
    invokeLater
    0.52
     geslacht
    0.49
    findpost
    0.48
     jScrollPane
    0.48
    PhysRev
    0.47
    ]]);
    0.47
    ?):
    0.47
    Activations Density 3.607%

    No Known Activations