© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3848
    Prev
    Next
    INDEX
    Explanations

    words relating to technology

    oai_token-act-pair · gemini-2.0-flash

    tech

    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
     hjem
    -0.47
    geblich
    -0.46
     Mehl
    -0.46
     asiatique
    -0.45
    NTSTATUS
    -0.45
     sacré
    -0.45
    Gemeinden
    -0.44
    āk
    -0.43
     dévelo
    -0.43
     allAfrica
    -0.43
    POSITIVE LOGITS
    HostException
    0.71
     estekak
    0.71
    IntoConstraints
    0.71
    цездатний
    0.71
     Waray
    0.65
     CoreData
    0.63
    expandindo
    0.63
    новниш
    0.63
     AssemblyCulture
    0.63
    EDEFAULT
    0.62
    Activations Density 0.470%

    No Known Activations