© 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. 6066
    Prev
    Next
    INDEX
    Explanations

    terms related to technical specifications and parts.

    oai_token-act-pair · gemini-2.0-flash

    Mechanical components

    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
     pinulongan
    -1.05
    PreferredItem
    -0.74
     оригіналу
    -0.70
     <<<<<<<<<<<<<<
    -0.70
    WithIOException
    -0.68
    AddTagHelper
    -0.68
     auffi
    -0.67
     purpoſe
    -0.65
    WriteTagHelper
    -0.64
    ؤلاء
    -0.64
    POSITIVE LOGITS
     per
    0.54
    fällig
    0.48
    مصادر
    0.48
    Према
    0.45
    thma
    0.45
    endforeach
    0.42
     externi
    0.42
     gynhyrchwyd
    0.42
    JANE
    0.41
    uccio
    0.41
    Activations Density 2.731%

    No Known Activations