© 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. 4223
    Prev
    Next
    INDEX
    Explanations

    code-related keywords, especially related to conditional statements and logical operators.

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
    k
    -0.31
    ma
    -0.31
    po
    -0.29
    ka
    -0.28
    al
    -0.27
    ja
    -0.27
    ch
    -0.26
    ta
    -0.26
    ho
    -0.25
    li
    -0.25
    POSITIVE LOGITS
     enfans
    1.08
     avoient
    1.03
     ainfi
    1.02
     auroit
    1.02
     plufieurs
    1.02
     feroit
    0.98
     vérit
    0.98
     élas
    0.96
     mauvaises
    0.95
     quelcon
    0.95
    Activations Density 3.899%

    No Known Activations