© 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. 11970
    Prev
    Next
    INDEX
    Explanations

    different forms of the verb "to be"

    oai_token-act-pair · gemini-2.0-flash

    Personal impressions

    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
     hẹn
    -0.42
     bels
    -0.42
    غرافيا
    -0.41
    meyen
    -0.40
    neum
    -0.40
    denly
    -0.39
    ienka
    -0.39
     allem
    -0.38
    ведений
    -0.38
     plantilla
    -0.37
    POSITIVE LOGITS
     ModelExpression
    0.96
    setVerticalGroup
    0.88
    ⓧ
    0.82
    LabelTagHelper
    0.81
     disambiguazione
    0.78
    SharedDtor
    0.78
    expandindo
    0.74
    存于互联网档案馆
    0.73
    Datuak
    0.72
    ContentAsync
    0.72
    Activations Density 0.894%

    No Known Activations