© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5383
    Prev
    Next
    INDEX
    Explanations

    language inviting contact or interaction, particularly instructions and hyperlinks

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Learn
    -0.58
     learns
    -0.58
    learn
    -0.56
     learnt
    -0.53
     learning
    -0.52
    âce
    -0.51
     learned
    -0.49
     learn
    -0.49
     please
    -0.48
    hower
    -0.47
    POSITIVE LOGITS
     JpaRepository
    0.68
    setVerticalGroup
    0.63
    BagConstraints
    0.61
    WaitGroup
    0.58
    OpenHelper
    0.57
     GenerationType
    0.57
    enumi
    0.57
    XmlAccessorType
    0.57
    harvard
    0.56
     numberOfRows
    0.56
    Activations Density 8.290%

    No Known Activations