© 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. 1326
    Prev
    Next
    INDEX
    Explanations

    math or code block delimiters

    oai_token-act-pair · gemini-2.0-flash

    code and math

    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
    principalTable
    -0.54
    ագրություններ
    -0.49
    hyrchwyd
    -0.49
    SourceChecksum
    -0.48
    IVEREF
    -0.48
     jadx
    -0.48
     advantage
    -0.45
    Šaltiniai
    -0.45
    Étymologie
    -0.45
     uintptr
    -0.43
    POSITIVE LOGITS
     coû
    0.59
     enää
    0.59
    HostException
    0.59
     faibles
    0.57
    +#+#
    0.57
     fotografico
    0.57
     étoit
    0.57
     spesa
    0.56
     feroit
    0.56
     dépens
    0.56
    Activations Density 2.651%

    No Known Activations