© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3477
    Prev
    Next
    INDEX
    Explanations

    sentence fragments containing the verb "have".

    oai_token-act-pair · gemini-2.0-flash

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    umpang
    -0.67
    ashir
    -0.52
    trero
    -0.52
    Autowired
    -0.51
    pholes
    -0.50
    AndroidJUnit
    -0.50
     sewn
    -0.48
     الرا
    -0.48
    ennon
    -0.48
    ėl
    -0.47
    POSITIVE LOGITS
    StateList
    0.56
    secuencias
    0.52
     --}}
    0.49
    日閲覧
    0.49
    reportWebVitals
    0.49
    estacks
    0.48
    cato
    0.47
    Occurred
    0.47
     Enkel
    0.47
    JKLM
    0.47
    Activations Density 2.259%

    No Known Activations