© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5000
    Prev
    Next
    INDEX
    Explanations

    past tense verbs relating to creation, especially 'made'

    oai_token-act-pair · gemini-2.0-flash

    made

    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
    amse
    -0.56
     XCTest
    -0.54
     StatefulWidget
    -0.54
    $'
    -0.51
    Réalisation
    -0.48
     récomp
    -0.48
    зонта
    -0.47
    writeFieldEnd
    -0.46
     endfor
    -0.46
    Παραπομπές
    -0.46
    POSITIVE LOGITS
    WriteTagHelper
    0.65
     незавершена
    0.61
    ējās
    0.58
     available
    0.58
     TAMBÉM
    0.56
    PerformLayout
    0.54
    Personensuche
    0.54
    expandindo
    0.54
     CreateTagHelper
    0.53
     المعيارى
    0.53
    Activations Density 4.769%

    No Known Activations