© 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. 5643
    Prev
    Next
    INDEX
    Explanations

    scientific terms, especially chemical compounds and lab procedures, including phrases that specify examples.

    oai_token-act-pair · gemini-2.0-flash

    scientific research

    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
     ingredients
    -1.00
     INGREDIENTS
    -0.91
     ingredient
    -0.90
     Ingredients
    -0.90
    Ingredients
    -0.90
    Ingredient
    -0.88
    ingredients
    -0.87
     nutrients
    -0.83
     Ingredient
    -0.82
     nitrogen
    -0.77
    POSITIVE LOGITS
    featureID
    0.54
    SourceChecksum
    0.53
     initComponents
    0.52
    }),
    0.48
     autorytatywna
    0.47
     digress
    0.47
    shund
    0.47
    HideFlags
    0.47
     Paglinawan
    0.47
    )$/,
    0.46
    Activations Density 5.719%

    No Known Activations