© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 710
    Prev
    Next
    INDEX
    Explanations

    the word "a" followed by certain quantifiers, especially "month", "year", "couple", or "few".

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     defaultstate
    -0.95
    couple
    -0.91
     couple
    -0.84
     Couple
    -0.79
     coppia
    -0.77
    rawDesc
    -0.76
    Couple
    -0.75
    GEBURTSDATUM
    -0.72
    GIVEREF
    -0.72
     internetowa
    -0.71
    POSITIVE LOGITS
     a
    0.46
    onya
    0.40
     just
    0.40
    setImageResource
    0.40
    ayette
    0.39
    orias
    0.39
     spec
    0.39
    ingos
    0.38
    uestamente
    0.38
    ingo
    0.38
    Activations Density 1.142%

    No Known Activations