© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4138
    Prev
    Next
    INDEX
    Explanations

    words indicating a change or process is occurring

    oai_token-act-pair · 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
     فريبيس
    -0.51
    sidemargin
    -0.47
     Процитовано
    -0.41
    istoitu
    -0.41
    care
    -0.40
     AssemblyVersion
    -0.40
     care
    -0.38
     MongoClient
    -0.37
     Vordergrund
    -0.37
    bootstrapcdn
    -0.36
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.73
     strongly
    0.71
     normally
    0.66
    Personendaten
    0.66
    EndGlobalSection
    0.66
     extensively
    0.65
    rinha
    0.65
     intimately
    0.64
    Trayectoria
    0.63
     kindly
    0.62
    Activations Density 2.774%

    No Known Activations