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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 13507
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to posing a question or stating a fact or situation, especially with supporting details

    oai_token-act-pair · gemini-2.0-flash

    Determining truth and accountability

    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
     continue
    -0.66
    ChildScrollView
    -0.57
    volve
    -0.54
     createContext
    -0.49
    complexType
    -0.49
     StringField
    -0.48
    nocache
    -0.47
     Continue
    -0.47
    RTLD
    -0.47
    ITECH
    -0.46
    POSITIVE LOGITS
     predicts
    0.78
     gets
    0.74
     grows
    0.73
     adds
    0.72
     indicates
    0.72
     reflects
    0.72
     tells
    0.71
     gives
    0.71
     improves
    0.71
     extends
    0.71
    Activations Density 17.027%

    No Known Activations