© 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. 2539
    Prev
    Next
    INDEX
    Explanations

    words and short phrases in a variety of languages

    oai_token-act-pair · gemini-2.0-flash

    Code and 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
     cu
    -0.50
     ama
    -0.49
     due
    -0.47
    ēm
    -0.46
    era
    -0.46
     les
    -0.46
     toma
    -0.43
    IVEREF
    -0.42
    ples
    -0.42
    kách
    -0.42
    POSITIVE LOGITS
     ویکی‌پدیای
    0.79
     виправивши
    0.74
     initComponents
    0.70
    Personensuche
    0.68
     <=",
    0.66
     CreateTagHelper
    0.66
     religieuses
    0.66
    uxxxx
    0.65
     maternidade
    0.65
    StoryboardSegue
    0.64
    Activations Density 0.453%

    No Known Activations