© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5656
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially related to CSS and HTML

    oai_token-act-pair · gemini-2.0-flash

    CSS

    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
    GOTREF
    -0.71
     المعيارى
    -0.66
    RefNanny
    -0.66
    شهاد
    -0.64
     snippetHide
    -0.63
    UserScript
    -0.62
    TagHelper
    -0.60
    ArgsConstructor
    -0.60
    +#+
    -0.59
    +#+#
    -0.57
    POSITIVE LOGITS
     hair
    1.18
     Hair
    1.13
    HAIR
    1.04
    Hair
    1.01
    hair
    1.00
     hairstyle
    0.99
     haircut
    0.97
     hairdresser
    0.97
     styling
    0.96
     HAIR
    0.96
    Activations Density 0.576%

    No Known Activations