© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10612
    Prev
    Next
    INDEX
    Explanations

    music-related text like song titles, musicians, or musical styles such as jazz

    oai_token-act-pair · gemini-2.0-flash

    technical jargon or programming-related terms

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    BeginContext
    -0.61
    Bronnen
    -0.60
     виправивши
    -0.57
    SystemColors
    -0.52
     demografica
    -0.47
    AndEndTag
    -0.47
    Coordenadas
    -0.46
     تانيه
    -0.46
     المعيارى
    -0.46
     року
    -0.45
    POSITIVE LOGITS
     AspNetCore
    0.60
     pinulongan
    0.57
    Thời
    0.54
     MLS
    0.53
     uVar
    0.52
     SUA
    0.52
    enol
    0.52
    })*/
    0.52
    fromCharCode
    0.52
    Terri
    0.50
    Activations Density 0.441%

    No Known Activations