© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6235
    Prev
    Next
    INDEX
    Explanations

    words expressing contrast, temporal proximity, or potential negative outcomes.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "before"

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

    before

    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
    mappedBy
    -0.52
    HasKey
    -0.41
     hö
    -0.40
    ignées
    -0.40
     mysqli
    -0.39
     ListTile
    -0.39
    ModelAdmin
    -0.38
    haustible
    -0.38
    BeanUtils
    -0.38
    jzen
    -0.37
    POSITIVE LOGITS
     before
    2.78
    before
    2.53
     Before
    2.44
    Before
    2.39
     BEFORE
    2.25
    BEFORE
    2.20
     antes
    2.20
     sebelum
    2.17
     prior
    2.16
     Antes
    1.95
    Activations Density 3.836%

    No Known Activations