© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15302
    Prev
    Next
    INDEX
    Explanations

    sentence structures that include auxiliary verbs conjugated in the past tense

    oai_token-act-pair · gemini-2.0-flash

    have

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     has
    -1.36
    has
    -1.13
     have
    -1.11
    Has
    -1.06
    been
    -0.98
     been
    -0.98
     telah
    -0.96
     Has
    -0.95
     hasn
    -0.93
     haven
    -0.93
    POSITIVE LOGITS
     propOrder
    0.98
    InSection
    0.96
     defaultstate
    0.91
    PropertyChanging
    0.89
     Roskov
    0.85
    Personensuche
    0.85
    хьтан
    0.84
     snippetHide
    0.82
    BagConstraints
    0.82
    /**
    0.82
    Activations Density 0.844%

    No Known Activations