© 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. 14402
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to history, politics, conflict, and ethical or moral issues.

    oai_token-act-pair · gemini-2.0-flash

    complex, nuanced arguments

    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
     समीक्षाओं
    -0.66
    adə
    -0.63
    ंदीखरीदारी
    -0.62
    MLLoader
    -0.58
    inflater
    -0.55
     mergeFrom
    -0.53
    ėk
    -0.53
    CrossRef
    -0.52
    ReusableCell
    -0.51
    DeleteBehavior
    -0.51
    POSITIVE LOGITS
    webElementXpaths
    0.59
    ∭
    0.54
     Shakspeare
    0.51
    raff
    0.50
    +#+#
    0.49
    twas
    0.48
    曖昧さ回避
    0.48
    jooq
    0.48
     religiously
    0.48
    CppCodeGen
    0.47
    Activations Density 22.336%

    No Known Activations