© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7911
    Prev
    Next
    INDEX
    Explanations

    paragraphs related to politics and government

    oai_token-act-pair · gemini-2.0-flash

    totally

    np_max-act · gemini-2.0-flash

    cabinet

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.92
     Monfieur
    -1.15
     themſelves
    -1.05
     pleaſure
    -1.03
     itſelf
    -1.01
     myſelf
    -0.98
     Jefus
    -0.96
     faſt
    -0.94
     ſever
    -0.94
     reaſon
    -0.93
    POSITIVE LOGITS
    awaiter
    0.72
    MathML
    0.72
     []:
    0.67
     مشين
    0.66
     }{@
    0.63
     zar
    0.61
    nar
    0.59
     שוליים
    0.58
     Stabilization
    0.58
    abestanden
    0.57
    Activations Density 1.441%

    No Known Activations