© 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. 4842
    Prev
    Next
    INDEX
    Explanations

    scientific text about material properties in specific directions

    oai_token-act-pair · gemini-2.0-flash

    Scientific direction and orientation

    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
     nonUne
    -0.65
    ValueStyle
    -0.63
     שוליים
    -0.60
    
    -0.60
    ագրություններ
    -0.60
    Tembelea
    -0.60
    сылкі
    -0.59
     Pingback
    -0.56
    Rujuakan
    -0.55
     disambiguazione
    -0.55
    POSITIVE LOGITS
    initializeApp
    0.65
    '">
    0.54
    GEBURTSDATUM
    0.50
    AOS
    0.48
     juiz
    0.47
    RectangleBorder
    0.47
    throw
    0.47
     zac
    0.47
    OZ
    0.46
     Erzb
    0.46
    Activations Density 2.934%

    No Known Activations