© 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. 14939
    Prev
    Next
    INDEX
    Explanations

    Canadian locations

    oai_token-act-pair · gemini-2.0-flash

    places

    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
    adpleegd
    -0.74
    TagMode
    -0.71
    kloped
    -0.68
    SharedCtor
    -0.66
    illots
    -0.64
    UrlResolution
    -0.62
     AssemblyCompany
    -0.60
     apud
    -0.60
    MessageTagHelper
    -0.59
    RenderAtEndOf
    -0.59
    POSITIVE LOGITS
    קישורים
    0.50
    SurfaceView
    0.48
    cedor
    0.47
     cal
    0.47
    AppRoutingModule
    0.46
    ichthys
    0.45
    তথ্যসূত্র
    0.45
    protoc
    0.45
    ตร
    0.44
    crate
    0.44
    Activations Density 0.745%

    No Known Activations