© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6713
    Prev
    Next
    INDEX
    Explanations

    the prefix "mas", highly correlated with the word "mastitis"

    oai_token-act-pair · gemini-2.0-flash

    mas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     the
    -0.70
     Mas
    -0.65
     beru
    -0.61
     digress
    -0.59
     I
    -0.56
     something
    -0.56
     Ke
    -0.55
    hadur
    -0.54
    né
    -0.53
    és
    -0.53
    POSITIVE LOGITS
     myſelf
    1.24
     Monfieur
    1.16
     leaſt
    1.13
     itſelf
    1.13
     houſe
    1.11
     themſelves
    1.09
     ſche
    1.09
     himſelf
    1.09
     Houſe
    1.09
     Theſe
    1.09
    Activations Density 0.505%

    No Known Activations