© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5596
    Prev
    Next
    INDEX
    Explanations

    mentions of law enforcement and legal documentation in an international context, especially related to India and Bangladesh

    oai_token-act-pair · gemini-2.0-flash

    technical terms or specific identifiers

    np_token-act-pair-logits · gpt-4o-mini

    police districts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    เอา
    -0.47
    Captor
    -0.46
    BorderFactory
    -0.42
    ждународ
    -0.40
    سبة
    -0.40
    OrNil
    -0.40
     swee
    -0.39
    PLER
    -0.39
    ệm
    -0.39
    elemField
    -0.38
    POSITIVE LOGITS
    expandindo
    0.76
    abetes
    0.66
     AssemblyCulture
    0.59
     Италијани
    0.58
    ANNES
    0.58
    WithMany
    0.57
    Ecotoxicity
    0.57
     kasarigan
    0.56
    vember
    0.53
    Balan
    0.53
    Activations Density 0.210%

    No Known Activations