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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13253
    Prev
    Next
    INDEX
    Explanations

    text in languages other than English, particularly Malay

    oai_token-act-pair · gemini-2.0-flash

    Malaysia

    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
    Tembelea
    -0.51
     lees
    -0.47
     Crews
    -0.44
    Haber
    -0.43
     USF
    -0.41
     hastened
    -0.41
     hanged
    -0.41
    δες
    -0.41
    IVersion
    -0.40
    RenderAtEndOf
    -0.40
    POSITIVE LOGITS
     Савезне
    0.69
     requestCode
    0.66
    Autoritní
    0.60
    IntoConstraints
    0.60
    SBATCH
    0.59
    VersionUID
    0.59
     WaitForSeconds
    0.59
    awtextra
    0.59
     Allociné
    0.58
    arraycopy
    0.58
    Activations Density 0.203%

    No Known Activations