© 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. 2922
    Prev
    Next
    INDEX
    Explanations

    scientific writing, especially about physics

    oai_token-act-pair · gemini-2.0-flash

    physics/field theory

    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
     Houſe
    -0.60
    AlterField
    -0.59
    évaluateur
    -0.56
     Allociné
    -0.52
    ArrowToggle
    -0.51
     Efq
    -0.50
     acordo
    -0.49
    ectoria
    -0.49
     SqlDbType
    -0.49
    xase
    -0.48
    POSITIVE LOGITS
     grà
    0.53
    oredCriteria
    0.53
    rawDesc
    0.53
    Personensuche
    0.52
    tvguidetime
    0.52
    
    0.52
    AsUp
    0.50
     '\\;'
    0.49
    enschap
    0.49
     Ann
    0.48
    Activations Density 6.098%

    No Known Activations