© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8519
    Prev
    Next
    INDEX
    Explanations

    descriptions of restaurants and bars

    oai_token-act-pair · gemini-2.0-flash

    Restaurants or hotels

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     MainAxisSize
    -0.90
     فريبيس
    -0.80
    NOPQRST
    -0.79
     Monfieur
    -0.78
    mergeFrom
    -0.76
     незавершена
    -0.75
     Wikimedijinoj
    -0.75
    CTO
    -0.72
     Jefus
    -0.72
     iſt
    -0.72
    POSITIVE LOGITS
    метров
    0.41
     Camp
    0.39
    sen
    0.37
    freie
    0.36
     ver
    0.35
     camp
    0.35
    lète
    0.35
     skóra
    0.35
    摘要
    0.35
     sen
    0.34
    Activations Density 0.945%

    No Known Activations