© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13277
    Prev
    Next
    INDEX
    Explanations

    verbs of motion

    oai_token-act-pair · gemini-2.0-flash

    indicating movement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    IBOutlet
    -0.66
    ArgsConstructor
    -0.65
    setVerticalGroup
    -0.65
     nakalista
    -0.64
    Демографія
    -0.61
    yntaxException
    -0.60
    AccessorTable
    -0.60
    IntoConstraints
    -0.60
    oa̍t
    -0.59
    énario
    -0.59
    POSITIVE LOGITS
    )++;
    0.54
     تضيفلها
    0.50
    HasKey
    0.44
     Efq
    0.44
     ſen
    0.44
     ſome
    0.43
    zzleHttp
    0.43
    tructive
    0.42
    */),
    0.41
    stood
    0.41
    Activations Density 0.619%

    No Known Activations