© 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. 6273
    Prev
    Next
    INDEX
    Explanations

    modal verbs such as "can," "will," and "would," often in the context of possibility or obligation

    oai_token-act-pair · 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
    พาะ
    -0.53
     gsx
    -0.45
    elf
    -0.44
    (;;)
    -0.42
    =$((
    -0.42
     wohnung
    -0.41
     becauſe
    -0.40
     alber
    -0.39
    吉祥
    -0.39
    éné
    -0.39
    POSITIVE LOGITS
     مشين
    0.98
    GEBURTSDATUM
    0.81
    tonode
    0.75
     nahilalakip
    0.71
     autorytatywna
    0.70
    Autoritní
    0.70
     cherchés
    0.66
     win
    0.66
     AssemblyCompany
    0.65
     CreateTagHelper
    0.64
    Activations Density 3.615%

    No Known Activations