© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12614
    Prev
    Next
    INDEX
    Explanations

    numbers with apostrophes, periods, and dashes.

    oai_token-act-pair · gemini-2.0-flash

    Government statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    principalColumn
    -0.76
     незавершена
    -0.59
    EDEFAULT
    -0.57
    +#+#
    -0.56
     tartalomajánló
    -0.53
    amentals
    -0.52
    InjectAttribute
    -0.50
    ViewFeatures
    -0.50
    ynchronously
    -0.49
    mergeFrom
    -0.48
    POSITIVE LOGITS
    mau
    0.52
     tremb
    0.52
    مل
    0.50
     telef
    0.49
     divis
    0.49
    utorial
    0.48
    FLU
    0.48
    uf
    0.48
     trình
    0.47
    ellen
    0.47
    Activations Density 0.248%

    No Known Activations