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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2678
    Prev
    Next
    INDEX
    Explanations

    words that appear to be conjunctions and adjectives particularly "strong"

    oai_token-act-pair · gemini-2.0-flash

    strong

    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
     strong
    -3.33
     Strong
    -3.27
    Strong
    -3.22
    strong
    -3.13
     strongest
    -2.91
     STRONG
    -2.89
     stronger
    -2.81
    STRONG
    -2.58
     Stronger
    -2.53
     sterke
    -2.14
    POSITIVE LOGITS
    Datuak
    0.66
    EClass
    0.59
    urnia
    0.58
    ServletException
    0.57
    RenderAtEndOf
    0.56
    ValueGenerated
    0.55
    脚注の使い方
    0.54
     getopt
    0.52
    UnsafeEnabled
    0.51
    verifyException
    0.51
    Activations Density 3.791%

    No Known Activations