© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8345
    Prev
    Next
    INDEX
    Explanations

    text discussing municipal planning and projects, often related to transportation.

    oai_token-act-pair · gemini-2.0-flash

    Governmental bodies and finances

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    انيف
    -0.57
    éges
    -0.54
    クリート
    -0.46
    ากาศ
    -0.46
     σχέ
    -0.43
     Plans
    -0.42
    PhysRev
    -0.42
     laten
    -0.42
     popo
    -0.42
    etern
    -0.40
    POSITIVE LOGITS
    contentLoaded
    0.84
    UnusedPrivate
    0.81
     AssemblyCulture
    0.79
    httphttps
    0.77
     okuyayım
    0.76
    Personendaten
    0.75
    AddTagHelper
    0.74
    yarnpkg
    0.70
    principalTable
    0.69
     تضيفلها
    0.68
    Activations Density 8.265%

    No Known Activations