© 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. 6319
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal and political conflict.

    oai_token-act-pair · gemini-2.0-flash

    past tense verbs related to operations or actions

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

    actions completed

    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
    ReusableCell
    -0.79
    ArrowToggle
    -0.79
    +#+#
    -0.77
    contentLoaded
    -0.74
     ComVisible
    -0.69
     Biôgrafia
    -0.69
    InjectAttribute
    -0.66
    Rhestr
    -0.66
    anadas
    -0.66
    #+#
    -0.65
    POSITIVE LOGITS
     undertaken
    0.96
     effectu
    0.94
     performed
    0.94
     conducted
    0.89
     executed
    0.87
     effected
    0.84
     completed
    0.84
     achieved
    0.82
     initiated
    0.80
     accomplished
    0.79
    Activations Density 5.790%

    No Known Activations