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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6073
    Prev
    Next
    INDEX
    Explanations

    words related to 3D computer graphics and game design

    oai_token-act-pair · gemini-2.0-flash

    technical or programming-related terms and code patterns

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

    Software and programming

    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
     oprot
    -0.56
     automatiques
    -0.54
     humaines
    -0.52
     culturelles
    -0.52
     tendances
    -0.50
     Kell
    -0.50
     giuri
    -0.48
     humains
    -0.47
     élevées
    -0.47
     supérieures
    -0.46
    POSITIVE LOGITS
    Datuak
    0.59
    AndEndTag
    0.58
     للمعارف
    0.58
    tagHelper
    0.57
    adaptiveStyles
    0.57
    \{\\
    0.54
    Архівовано
    0.53
    COUVER
    0.52
    FromArgb
    0.52
    JAKARTA
    0.52
    Activations Density 4.648%

    No Known Activations