© 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. 5579
    Prev
    Next
    INDEX
    Explanations

    words related to court proceedings and legal testimony

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "version"

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

    version

    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
    farwyddwr
    -0.50
    charis
    -0.41
    ียว
    -0.40
    GEBURTS
    -0.39
    itespace
    -0.39
     Distrikt
    -0.38
     mencetak
    -0.38
    المكان
    -0.38
     otomatig
    -0.38
    propTypes
    -0.37
    POSITIVE LOGITS
     version
    1.37
     versions
    1.29
    version
    1.22
     versión
    1.19
     versiones
    1.13
     versão
    1.12
     VERSION
    1.12
     Versions
    1.10
     Version
    1.09
     versione
    1.07
    Activations Density 3.619%

    No Known Activations