© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2827
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers following "from:" and "to:"

    oai_token-act-pair · gemini-2.0-flash

    x

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    RegistryLite
    -0.82
    Enllaces
    -0.78
    GEBURTSDATUM
    -0.76
     CreateTagHelper
    -0.75
     betweenstory
    -0.74
     viewDidLoad
    -0.73
     myſelf
    -0.72
     Италијани
    -0.71
    Personensuche
    -0.70
     endwhile
    -0.67
    POSITIVE LOGITS
    ResumeLayout
    0.43
    قایناق‌لار
    0.42
    યા
    0.42
    GeoNames
    0.41
    ämie
    0.39
     sin
    0.39
    enguaje
    0.38
     loaded
    0.38
    addImage
    0.37
     den
    0.37
    Activations Density 2.186%

    No Known Activations