© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11892
    Prev
    Next
    INDEX
    Explanations

    verbs (especially helping verbs) and associated pronouns and prepositions.

    oai_token-act-pair · gemini-2.0-flash

    verbs

    np_max-act · gemini-2.0-flash

    present-tense verbs

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     actuelles
    -0.53
    今は
    -0.52
     actuelle
    -0.51
     actuels
    -0.50
     ngayon
    -0.47
     attualmente
    -0.45
     obecnie
    -0.43
     actuales
    -0.42
     has
    -0.42
    aujourd
    -0.42
    POSITIVE LOGITS
    DockStyle
    1.07
    expandindo
    1.02
    protoimpl
    1.00
    AnchorStyles
    0.98
    SequentialGroup
    0.95
     AssemblyCompany
    0.94
    BeginContext
    0.93
     فريبيس
    0.90
    脚注の使い方
    0.90
    RenderAtEndOf
    0.89
    Activations Density 5.379%

    No Known Activations