© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8079
    Prev
    Next
    INDEX
    Explanations

    words containing "thy", "ne", "y", "2", "channe" or "paralle"

    oai_token-act-pair · gemini-2.0-flash

    chemistry

    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
    l
    -2.42
    lI
    -0.88
     l
    -0.81
    lO
    -0.79
    lha
    -0.77
    lz
    -0.77
    lsp
    -0.76
    lde
    -0.75
    lma
    -0.75
    lty
    -0.75
    POSITIVE LOGITS
     الحره
    0.67
    EndInit
    0.54
    NÍ
    0.50
    fford
    0.50
    IsContent
    0.50
    äť
    0.49
     ujednoznacz
    0.49
    ISTERS
    0.48
    Lever
    0.48
    ELAND
    0.48
    Activations Density 2.355%

    No Known Activations