© 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. 16336
    Prev
    Next
    INDEX
    Explanations

    words related to solar power and space-based observation

    oai_token-act-pair · gemini-2.0-flash

    solar

    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
    IntoConstraints
    -0.66
    AndEndTag
    -0.65
     surla
    -0.63
     Lehre
    -0.59
     Alamy
    -0.58
    ouac
    -0.57
     depositphotos
    -0.56
    TabIndex
    -0.56
     '\\;'
    -0.56
    CrossRef
    -0.55
    POSITIVE LOGITS
    TestTools
    0.49
    ches
    0.48
     emas
    0.43
    CESO
    0.39
    httphttps
    0.39
    class
    0.39
     shareholders
    0.38
     ov
    0.38
    ary
    0.37
    openConnection
    0.37
    Activations Density 2.974%

    No Known Activations