© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5072
    Prev
    Next
    INDEX
    Explanations

    the words 'max' and 'min', often in programming contexts

    oai_token-act-pair · gemini-2.0-flash

    maximal values and types

    np_token-act-pair-logits · gpt-4o-mini

    max

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    帖最后由
    -0.61
     kasarigan
    -0.61
     насељу
    -0.59
     AssemblyCulture
    -0.57
     Roskov
    -0.54
    IUrlHelper
    -0.53
    SequentialGroup
    -0.52
    :✨
    -0.52
    Steady
    -0.52
     Walkover
    -0.51
    POSITIVE LOGITS
    ismet
    0.57
     որ
    0.50
    SCM
    0.49
     alimentaria
    0.49
     šķ
    0.49
    SE
    0.49
     dø
    0.48
     SCM
    0.47
    InstanceState
    0.47
     colony
    0.46
    Activations Density 2.051%

    No Known Activations