© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11189
    Prev
    Next
    INDEX
    Explanations

    specifications and parts for a car engine

    oai_token-act-pair · gemini-2.0-flash

    engine specifications and documents

    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
    IUrlHelper
    -0.52
    
    -0.49
     utafitiHapana
    -0.48
    ніципа
    -0.48
    合作
    -0.47
    ineno
    -0.47
    ষ্
    -0.46
     perioden
    -0.46
    vician
    -0.45
     aspetta
    -0.45
    POSITIVE LOGITS
     resourceCulture
    0.63
    SPJ
    0.59
     }}"></
    0.57
    BoxShadow
    0.56
    EndProject
    0.53
    ագրություններ
    0.53
    agisse
    0.51
    EndTag
    0.51
    spesies
    0.51
     TAP
    0.50
    Activations Density 0.630%

    No Known Activations