© 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
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4143
    Prev
    Next
    INDEX
    Explanations

    code syntax for the Marlin UI, including references to TFT, color and screen elements

    oai_token-act-pair · gemini-2.0-flash

    Code and GUI related text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     tartalomajánló
    -0.55
    -------
    -0.47
    mbggenerated
    -0.46
    一提
    -0.45
     organismo
    -0.43
    žnost
    -0.43
    singleton
    -0.43
     ragioni
    -0.41
    hæng
    -0.41
    NullCheck
    -0.41
    POSITIVE LOGITS
     Paglinawan
    0.63
    sizeCache
    0.60
     Thra
    0.57
    LEADING
    0.54
     gutter
    0.54
    lante
    0.54
    imageshack
    0.53
     Ignorance
    0.53
    pX
    0.52
    otheby
    0.52
    Activations Density 1.550%

    No Known Activations