© 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. 14862
    Prev
    Next
    INDEX
    Explanations

    words related to formal analysis or reports

    oai_token-act-pair · gemini-2.0-flash

    reporting facts

    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
     beginnetje
    -0.65
     ComVisible
    -0.58
    DetailComponent
    -0.54
     gopro
    -0.54
    ContainerState
    -0.54
     nemlig
    -0.53
    schirm
    -0.52
     picioare
    -0.52
     InputDecoration
    -0.52
    wpi
    -0.51
    POSITIVE LOGITS
     متعلقه
    0.73
    tagHelperRunner
    0.62
    Datuak
    0.58
     дописавши
    0.56
     CommonModule
    0.54
     Noi
    0.53
    zon
    0.52
     noi
    0.51
    cydow
    0.51
    ContentAsync
    0.50
    Activations Density 4.222%

    No Known Activations