© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 8201
    Prev
    Next
    INDEX
    Explanations

    words related to understanding or expressing knowledge and confusion, often in the context of creative works or abstract concepts

    oai_token-act-pair · gemini-2.0-flash

    induction/reproduction

    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
     esternos
    -0.67
     ReactDOM
    -0.56
     privées
    -0.54
     '\\;'
    -0.54
    ThroughAttribute
    -0.54
     transfieras
    -0.54
     MessageBoxIcon
    -0.53
    <bos>
    -0.52
     vectorielle
    -0.52
     nakalista
    -0.52
    POSITIVE LOGITS
     accumulate
    0.66
     induc
    0.62
     procur
    0.62
    Partici
    0.62
     perpetuate
    0.62
     intensify
    0.60
     retain
    0.60
     Reproduce
    0.60
     depict
    0.59
     facilitate
    0.59
    Activations Density 5.520%

    No Known Activations