© 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. 3899
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal, educational, and substance use topics.

    oai_token-act-pair · gemini-2.0-flash

    Sentence starters

    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
    WebVitals
    -0.56
     kasarigan
    -0.52
     utafitiHapana
    -0.52
    saraba
    -0.46
    Билгалдахарш
    -0.45
    webElementXpaths
    -0.42
    istoitu
    -0.39
     himo
    -0.39
    fortawesome
    -0.39
     NgModule
    -0.38
    POSITIVE LOGITS
     Then
    1.71
     Here
    1.59
     Because
    1.56
     That
    1.52
     While
    1.52
     Also
    1.52
     Such
    1.52
     Whether
    1.51
     Now
    1.51
     When
    1.50
    Activations Density 37.154%

    No Known Activations