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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 366
    Prev
    Next
    INDEX
    Explanations

    Spanish code or code snippets, and spanish stop words

    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
    Datuak
    -0.60
    HideFlags
    -0.54
     Baillargeon
    -0.52
     pleaſure
    -0.52
     Normdatei
    -0.52
    ništvo
    -0.50
    IntoConstraints
    -0.50
    PerformLayout
    -0.49
     nakalista
    -0.49
    Personendaten
    -0.47
    POSITIVE LOGITS
    enterOuterAlt
    0.57
    ineri
    0.51
     lendemain
    0.50
    ūsų
    0.49
    jface
    0.49
     électroniques
    0.48
    曖昧さ回避
    0.47
     vogliamo
    0.47
     beginnetje
    0.47
    onComplete
    0.47
    Activations Density 3.348%

    No Known Activations