© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 3545
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to changes of state, typically using the verb "to be" or similar verbs like "become"

    oai_token-act-pair · gemini-2.0-flash

    negative health situations

    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
     inflater
    -0.56
     Nis
    -0.52
     Schatz
    -0.49
    Obrázky
    -0.48
    ückt
    -0.47
    afterEach
    -0.47
    vaadin
    -0.47
     astore
    -0.47
    ="#
    -0.46
     protoimpl
    -0.46
    POSITIVE LOGITS
     ill
    0.62
     pregnant
    0.61
     depressed
    0.57
    amitié
    0.55
    uxxxx
    0.54
     Pregnant
    0.52
     sick
    0.52
     jealous
    0.51
    orced
    0.50
     poisoned
    0.50
    Activations Density 1.696%

    No Known Activations