© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15470
    Prev
    Next
    INDEX
    Explanations

    technical writing related to math, physics, or engineering

    oai_token-act-pair · gemini-2.0-flash

    numerical methods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    UEZ
    -0.46
     webdriver
    -0.45
    principalColumn
    -0.45
    rxjs
    -0.44
     CAL
    -0.44
    ṳ
    -0.43
     Cal
    -0.43
     cal
    -0.42
    TagMode
    -0.42
     Kal
    -0.41
    POSITIVE LOGITS
     nakalista
    0.79
     تضيفلها
    0.69
    Tikang
    0.68
     consultato
    0.65
    Datuak
    0.64
     betweenstory
    0.64
    出版年
    0.63
    AxisAlignment
    0.61
     Audiodateien
    0.60
    جغرافيا
    0.59
    Activations Density 6.438%

    No Known Activations