© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 3228
    Prev
    Next
    INDEX
    Explanations

    terms related to computer graphics

    oai_token-act-pair · gemini-2.0-flash

    computer filepaths and textures

    np_max-act · gemini-2.0-flash

    texture

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     in
    -0.85
    a
    -0.84
    ,
    -0.80
    i
    -0.79
     and
    -0.79
    n
    -0.77
     or
    -0.77
    /
    -0.75
    m
    -0.75
    ↵↵
    -0.75
    POSITIVE LOGITS
    ^(@)
    1.45
     myſelf
    1.45
     Theſe
    1.35
    >\<^
    1.33
     Efq
    1.30
     itſelf
    1.23
     الحره
    1.23
     AssemblyCulture
    1.22
    ."));
    1.20
     Monfieur
    1.20
    Activations Density 1.616%

    No Known Activations