© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13028
    Prev
    Next
    INDEX
    Explanations

    uses of the words "was", "is", "then", and "and"

    oai_token-act-pair · gemini-2.0-flash

    past tense verbs related to being

    np_token-act-pair-logits · gpt-4o-mini

    was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    LElement
    -0.54
     للمعارف
    -0.54
     cherchés
    -0.52
    ativement
    -0.52
    رشف
    -0.49
     vuitton
    -0.49
    اشتم
    -0.48
     defStyle
    -0.47
     înce
    -0.47
    esModule
    -0.47
    POSITIVE LOGITS
     predeceased
    0.59
    TestingModule
    0.57
     born
    0.56
     reared
    0.55
    onded
    0.54
    XmlAccessType
    0.53
    rimp
    0.52
    parsedMessage
    0.52
    odule
    0.49
     Pard
    0.48
    Activations Density 0.373%

    No Known Activations