© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15170
    Prev
    Next
    INDEX
    Explanations

    technical documents about signal processing, particularly emphasizing the relationship between input and output signals

    oai_token-act-pair · gemini-2.0-flash

    coding and user input

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     input
    -2.02
    input
    -1.94
     Input
    -1.85
    Input
    -1.81
     inputs
    -1.78
     INPUT
    -1.68
    INPUT
    -1.59
    输入
    -1.59
     Inputs
    -1.56
    inputs
    -1.47
    POSITIVE LOGITS
     pinulongan
    0.79
    wezen
    0.54
    JKLM
    0.52
    extérieur
    0.51
     MainAxisSize
    0.50
     Sciento
    0.50
    Datuak
    0.48
    piac
    0.48
    }$​
    0.48
     kasarigan
    0.47
    Activations Density 0.881%

    No Known Activations