© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8910
    Prev
    Next
    INDEX
    Explanations

    words ending in "izing", especially "maximizing" and "minimizing", often related to technical or mathematical contexts

    oai_token-act-pair · gemini-2.0-flash

    maximizing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    unic
    -0.61
     feiner
    -0.52
     amet
    -0.49
    BRI
    -0.46
     Olympedia
    -0.45
    ://"
    -0.45
     mano
    -0.45
     familiar
    -0.44
    asilan
    -0.44
     finer
    -0.44
    POSITIVE LOGITS
     maximum
    1.52
     Maximum
    1.41
     MAXIMUM
    1.40
     max
    1.39
    maximum
    1.38
     MAX
    1.37
     maxim
    1.36
    Maximum
    1.31
     maximal
    1.31
    maxim
    1.28
    Activations Density 0.331%

    No Known Activations