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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14152
    Prev
    Next
    INDEX
    Explanations

    code snippets using programming keywords and related terms.

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Efq
    -0.90
     raiſ
    -0.88
     doubtnut
    -0.78
    ſelf
    -0.78
     ―――――
    -0.77
     XNUMX
    -0.76
     myſelf
    -0.76
     crdi
    -0.75
    évaluateur
    -0.75
     bershka
    -0.75
    POSITIVE LOGITS
     intermédiaire
    0.60
     épaules
    0.60
     travailleurs
    0.58
     pouvoirs
    0.54
     lèvres
    0.54
     oídos
    0.54
     gouvernements
    0.53
     bolsillos
    0.52
     vérit
    0.51
     lumières
    0.51
    Activations Density 5.927%

    No Known Activations