© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12257
    Prev
    Next
    INDEX
    Explanations

    the name "Del"

    oai_token-act-pair · gemini-2.0-flash

    Del

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    WindowEvent
    -0.53
     dis
    -0.43
    enumi
    -0.43
    Palmarès
    -0.42
     Spitze
    -0.40
    knex
    -0.40
     Unidas
    -0.40
     domestiques
    -0.39
     ostavi
    -0.39
     catalana
    -0.39
    POSITIVE LOGITS
     CreateTagHelper
    0.68
    AndEndTag
    0.65
    IndentedString
    0.62
    Portale
    0.60
     Efq
    0.59
    FormTagHelper
    0.59
    Portály
    0.59
    <?
    0.59
    ."));
    0.58
    rinhos
    0.57
    Activations Density 0.497%

    No Known Activations