© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5940
    Prev
    Next
    INDEX
    Explanations

    words and abbreviations relating to proteins and enzymes, particularly in a biological or chemical context.

    oai_token-act-pair · gemini-2.0-flash

    ending in -mycin/-osine/-ase/-tokine/-leukin

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     EconPapers
    -0.67
    )");
    -0.54
    )";
    -0.49
    帖最后由
    -0.48
    "},
    -0.48
    }(),
    -0.48
     cherchés
    -0.48
     snippetHide
    -0.48
     GenerationType
    -0.47
    куртка
    -0.46
    POSITIVE LOGITS
    omycin
    0.79
    enosine
    0.70
    hydrogenase
    0.67
    rosine
    0.67
    amycin
    0.65
    rimidine
    0.65
    athione
    0.62
    tokine
    0.62
    chymal
    0.62
    leukin
    0.62
    Activations Density 14.713%

    No Known Activations