© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12264
    Prev
    Next
    INDEX
    Explanations

    words related to research, academic fields, and scientific writing.

    oai_token-act-pair · gemini-2.0-flash

    iese

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     mahdol
    -0.50
     võimal
    -0.46
    inga
    -0.45
     esetben
    -0.44
     vicini
    -0.43
     möj
    -0.43
     erős
    -0.41
     longues
    -0.41
     mukana
    -0.40
    adda
    -0.40
    POSITIVE LOGITS
    principalColumn
    0.78
     становника
    0.76
    makeConstraints
    0.74
     JpaRepository
    0.73
    Демографія
    0.70
     MainAxisSize
    0.70
    IntoConstraints
    0.69
     demografica
    0.68
    setVerticalGroup
    0.68
     GenerationType
    0.67
    Activations Density 23.826%

    No Known Activations