© 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. 10649
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to imprisonment, jails, sentences, and courts

    oai_token-act-pair · gemini-2.0-flash

    Incarceration

    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
     release
    -1.52
     released
    -1.40
     Release
    -1.37
     releasing
    -1.34
     releases
    -1.34
    release
    -1.34
     RELEASE
    -1.29
    Release
    -1.27
     Released
    -1.24
    released
    -1.24
    POSITIVE LOGITS
    الحياه
    0.57
    @[+][
    0.55
    Pyx
    0.55
    íncia
    0.54
    хьтан
    0.50
     estimés
    0.50
    Климат
    0.49
    kloped
    0.49
     patrie
    0.48
     antemano
    0.48
    Activations Density 0.602%

    No Known Activations