© 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. 669
    Prev
    Next
    INDEX
    Explanations

    sentences starting with "if", "that", or time-related words such as "when"

    oai_token-act-pair · gemini-2.0-flash

    if

    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
     itſelf
    -0.91
     myſelf
    -0.87
     pleaſure
    -0.85
     thyself
    -0.85
     ujednoznacz
    -0.81
     photolibrary
    -0.81
     raiſ
    -0.81
    Tembelea
    -0.81
    LookAnd
    -0.79
     themſelves
    -0.79
    POSITIVE LOGITS
     you
    2.34
     você
    0.87
     vous
    0.82
     شما
    0.68
     вам
    0.68
    you
    0.68
     вами
    0.63
     You
    0.60
     anda
    0.60
     Anda
    0.59
    Activations Density 0.709%

    No Known Activations