© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10174
    Prev
    Next
    INDEX
    Explanations

    words related to economy, politics, disasters, crime, and utilities

    oai_token-act-pair · 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
     ostavi
    -0.94
     vectorielle
    -0.83
     nuages
    -0.81
     morire
    -0.75
     racines
    -0.72
    DebuggerNonUser
    -0.72
     vectorielles
    -0.71
     colonnes
    -0.71
     vectoriales
    -0.70
    клопе
    -0.70
    POSITIVE LOGITS
     led
    0.44
    벳
    0.42
    ava
    0.41
    AVA
    0.40
    thio
    0.39
     pate
    0.38
    uesia
    0.37
    ENI
    0.37
     Bassett
    0.36
     fay
    0.35
    Activations Density 2.526%

    No Known Activations