© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4509
    Prev
    Next
    INDEX
    Explanations

    clauses with a personal pronoun followed by auxiliary verbs or present participles used to describe actions and experiences

    oai_token-act-pair · gemini-2.0-flash

    synonyms for always

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     ExecuteAsync
    -0.81
    Spoljašnje
    -0.65
    енча
    -0.63
    fetchone
    -0.58
     Мексичка
    -0.56
     snippetHide
    -0.56
     للاسماء
    -0.56
    ็จ
    -0.55
     GenerationType
    -0.55
     mxArray
    -0.55
    POSITIVE LOGITS
    always
    0.72
    ตลอด
    0.69
     always
    0.68
    whole
    0.65
     whole
    0.62
    throughout
    0.60
     siempre
    0.60
    Always
    0.58
     throughout
    0.57
     Always
    0.56
    Activations Density 1.059%

    No Known Activations