© 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. 414
    Prev
    Next
    INDEX
    Explanations

    technical language used in physics papers that discuss gases and magnets

    oai_token-act-pair · gemini-2.0-flash

    physics

    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
    TagMode
    -1.05
    SourceChecksum
    -0.82
     незавершена
    -0.76
    styleable
    -0.71
     onCancelled
    -0.70
    Hentet
    -0.69
    OGND
    -0.69
    LEncoder
    -0.68
    ArgumentParser
    -0.67
     nonUne
    -0.66
    POSITIVE LOGITS
     bound
    0.49
    ellite
    0.48
     muro
    0.46
    >[]
    0.46
     thunder
    0.45
     impenetrable
    0.45
     cort
    0.45
     compradores
    0.44
     impermeable
    0.43
    بسم
    0.43
    Activations Density 4.394%

    No Known Activations