© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1303
    Prev
    Next
    INDEX
    Explanations

    the word "where" (likely in mathematical contexts)

    oai_token-act-pair · gemini-2.0-flash

    where

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     
    -0.57
     One
    -0.43
     Red
    -0.43
     "
    -0.41
     P
    -0.41
    ensed
    -0.40
     $\
    -0.40
     Go
    -0.39
     tu
    -0.39
     La
    -0.39
    POSITIVE LOGITS
    UnusedPrivate
    0.98
     Cæsar
    0.96
    IntoConstraints
    0.95
     tartalomajánló
    0.94
     Monfieur
    0.93
     Majefty
    0.90
     poffible
    0.89
     odkazy
    0.86
     themſelves
    0.84
     pleaſure
    0.84
    Activations Density 0.564%

    No Known Activations