© 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. 4724
    Prev
    Next
    INDEX
    Explanations

    code or data strings, particularly from programming languages

    oai_token-act-pair · gemini-2.0-flash

    programming variables

    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
    RSpec
    -0.58
    Спасылкі
    -0.50
    AppCompat
    -0.50
    onViewCreated
    -0.50
    ock
    -0.47
    iastical
    -0.46
    ammans
    -0.45
    mith
    -0.45
    ARO
    -0.44
    LEAN
    -0.44
    POSITIVE LOGITS
     variable
    1.33
     Variable
    1.14
    Variable
    1.06
    variable
    1.04
     VARIABLE
    0.93
    变量
    0.80
     vettoriale
    0.74
     column
    0.71
    VARIABLE
    0.69
    column
    0.67
    Activations Density 13.769%

    No Known Activations