© 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. 4113
    Prev
    Next
    INDEX
    Explanations

    code snippets in Spanish and Javascript mixed together

    oai_token-act-pair · gemini-2.0-flash

    foreign languages

    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
    xtext
    -0.57
     <>",
    -0.53
    HasOne
    -0.53
     cantons
    -0.52
    awtextra
    -0.52
     Mijn
    -0.51
    phrine
    -0.50
    าศ
    -0.50
    IsPostBack
    -0.50
     authorities
    -0.49
    POSITIVE LOGITS
    存于互联网档案馆
    0.61
     kasarigan
    0.54
    udesta
    0.52
     فريبيس
    0.50
     GoogleFonts
    0.48
    \{\\
    0.47
    posedge
    0.45
    UseVisualStyle
    0.44
    følgelig
    0.44
    ReadByte
    0.43
    Activations Density 0.641%

    No Known Activations