© 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. 984
    Prev
    Next
    INDEX
    Explanations

    weighted terms in legal or technical documents

    oai_token-act-pair · gemini-2.0-flash

    weight

    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
     weight
    -2.88
     weigh
    -2.77
    weight
    -2.75
    Weight
    -2.72
     weights
    -2.70
     Weight
    -2.69
     WEIGHT
    -2.66
     weighed
    -2.59
     weighing
    -2.59
     weighs
    -2.56
    POSITIVE LOGITS
    ∮
    0.52
    Rohy
    0.47
     незавершена
    0.45
     Италијани
    0.43
    ดน
    0.43
    tidase
    0.42
     croissants
    0.42
     ticket
    0.42
    veden
    0.42
    nambuco
    0.42
    Activations Density 2.583%

    No Known Activations