© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6747
    Prev
    Next
    INDEX
    Explanations

    scientific terminology of various kinds with some focus on biology or chemistry

    oai_token-act-pair · gemini-2.0-flash

    frequency

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     оригіналу
    -0.54
    ▍
    -0.54
     незавершена
    -0.49
    Personendaten
    -0.49
    ViewInit
    -0.48
     NSCoder
    -0.48
    octanol
    -0.48
     neurom
    -0.47
    ContentLoaded
    -0.46
    olyte
    -0.46
    POSITIVE LOGITS
     frequency
    1.27
    frequency
    1.10
     Frequency
    1.10
    Frequency
    1.07
     frequencies
    1.05
    frequencies
    0.96
    freq
    0.94
    sizeCache
    0.92
    频率
    0.90
     FREQUENCY
    0.90
    Activations Density 1.744%

    No Known Activations