© 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. 15468
    Prev
    Next
    INDEX
    Explanations

    mentions of numbers, especially percentages, currency, and amounts

    oai_token-act-pair · gemini-2.0-flash

    Numbers and statistics

    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
    נת
    -0.57
     ActionBar
    -0.53
    onné
    -0.50
    nop
    -0.49
    Gemeinden
    -0.47
    ểu
    -0.47
     Arenas
    -0.47
     незавершена
    -0.46
    giques
    -0.46
     propOrder
    -0.46
    POSITIVE LOGITS
     pleaſure
    0.74
     protoimpl
    0.72
     houſe
    0.69
     ſtate
    0.68
     preſent
    0.64
     Jefus
    0.64
     reaſon
    0.63
     purpoſe
    0.63
     neceff
    0.62
    IntoConstraints
    0.62
    Activations Density 11.588%

    No Known Activations