© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11958
    Prev
    Next
    INDEX
    Explanations

    words related to government and processes within governmental/legal systems

    oai_token-act-pair · gemini-2.0-flash

    Official documents and procedures

    np_max-act-logits · gemini-2.0-flash

    say "function words"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     politiker
    -0.45
     orale
    -0.44
     myndig
    -0.43
     însă
    -0.42
     déput
    -0.41
     wiedzieć
    -0.40
     estação
    -0.39
     maail
    -0.39
    abetes
    -0.39
     colectiva
    -0.38
    POSITIVE LOGITS
     came
    0.90
     ran
    0.84
     fell
    0.82
     gave
    0.80
     did
    0.80
    — 
    0.77
     took
    0.76
     rang
    0.75
     became
    0.74
     hit
    0.73
    Activations Density 42.960%

    No Known Activations