© 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. 598
    Prev
    Next
    INDEX
    Explanations

    noun phrases related to medical conditions, diseases, or causes for them, as well as shifts or changes between states

    oai_token-act-pair · gemini-2.0-flash

    technical jargon

    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
     known
    -2.63
     Known
    -2.61
    Known
    -2.56
    known
    -2.48
     KNOWN
    -2.36
     conocida
    -1.84
     conocido
    -1.80
     conhecido
    -1.79
    KNOWN
    -1.77
     conhecida
    -1.77
    POSITIVE LOGITS
    <>());
    0.64
    SequentialGroup
    0.56
     gener
    0.52
    expandindo
    0.48
    uginosa
    0.47
     sometimes
    0.45
    uio
    0.44
    ynthesis
    0.43
    tij
    0.43
     cod
    0.43
    Activations Density 3.011%

    No Known Activations