© 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. 4998
    Prev
    Next
    INDEX
    Explanations

    instances of "ground" followed by another word, or "clouds"

    oai_token-act-pair · gemini-2.0-flash

    ground

    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
    IVEREF
    -0.75
    sizeCache
    -0.75
    PerformLayout
    -0.74
    ContentAsync
    -0.73
    IntoConstraints
    -0.73
     виправивши
    -0.69
     Italijanski
    -0.68
    findpost
    -0.66
    Datuak
    -0.65
     AspNetCore
    -0.65
    POSITIVE LOGITS
    SuccessListener
    0.41
    LayoutInflater
    0.41
    blocker
    0.40
     ::=
    0.40
    strdup
    0.40
     chính
    0.39
     clung
    0.38
    pop
    0.38
     AssemblyTitle
    0.38
     hoes
    0.38
    Activations Density 1.751%

    No Known Activations