© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12852
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions that are necessary or involve prepositions and articles related to these actions.

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     dignité
    -0.53
     spagno
    -0.48
     paire
    -0.48
    曖昧さ回避
    -0.48
     innamor
    -0.46
     leçon
    -0.45
     direttamente
    -0.44
     giapp
    -0.43
     perte
    -0.43
     lusso
    -0.42
    POSITIVE LOGITS
    httphttps
    0.91
    UserScript
    0.90
    mybatisplus
    0.79
     Normdatei
    0.73
    下载附件
    0.71
    Erreferentziak
    0.70
    %")
    0.70
    TagMode
    0.69
     EconPapers
    0.68
     ***/
    0.65
    Activations Density 1.382%

    No Known Activations