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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8667
    Prev
    Next
    INDEX
    Explanations

    code snippets including angle calculations, matrix operations, graphics drawing, loops, conditional logic, and button elements.

    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
     PIR
    -0.49
     SCOT
    -0.40
    IR
    -0.39
    PIR
    -0.39
    if
    -0.38
     OPC
    -0.38
     Berber
    -0.37
     EFT
    -0.37
     Kuwa
    -0.36
     FIR
    -0.36
    POSITIVE LOGITS
     supérieurs
    0.93
     définiti
    0.92
    rungsseite
    0.87
     colorés
    0.86
     démocr
    0.85
     fermés
    0.84
    migrationBuilder
    0.83
     disambiguazione
    0.82
     normaux
    0.82
     blessés
    0.81
    Activations Density 31.574%

    No Known Activations