© 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. 6004
    Prev
    Next
    INDEX
    Explanations

    words relating to government agencies, justice system, and business administration.

    oai_token-act-pair · gemini-2.0-flash

    titles and positions

    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
     pluie
    -0.73
     Company
    -0.72
     défaite
    -0.71
     Group
    -0.71
     Service
    -0.69
     Party
    -0.69
     planète
    -0.68
     larmes
    -0.68
     colère
    -0.68
     Plan
    -0.67
    POSITIVE LOGITS
     academy
    0.68
     federation
    0.65
     ambassador
    0.63
     queen
    0.62
     council
    0.62
     museum
    0.62
     hall
    0.61
     tartalomajánló
    0.61
     commissioner
    0.61
     alliance
    0.60
    Activations Density 6.859%

    No Known Activations