© 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. 723
    Prev
    Next
    INDEX
    Explanations

    words related to communication and language, particularly in formal settings

    oai_token-act-pair · gemini-2.0-flash

    academic/technical documents

    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
    mybatisplus
    -0.64
    tagext
    -0.52
    RegressionTest
    -0.51
     createState
    -0.48
    omock
    -0.47
    chluss
    -0.45
    onViewCreated
    -0.43
    SourceChecksum
    -0.42
     Kevin
    -0.41
     везе
    -0.41
    POSITIVE LOGITS
     foon
    0.59
     odkazy
    0.57
     StyleSheet
    0.55
    Literatuur
    0.55
    StyleSheet
    0.54
     CrossRef
    0.54
    requipa
    0.54
     sumpay
    0.53
    ſelf
    0.53
     registers
    0.53
    Activations Density 7.461%

    No Known Activations