© 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. 8633
    Prev
    Next
    INDEX
    Explanations

    snippets of internet chat, including usernames, time stamps, and message content

    oai_token-act-pair · gemini-2.0-flash

    multiple languages

    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
    Джерела
    -0.61
    تقاوى
    -0.54
    setDo
    -0.52
    ustimmung
    -0.50
    Personendaten
    -0.50
     hello
    -0.50
    fromnode
    -0.48
    ettür
    -0.48
    äuser
    -0.48
    čenje
    -0.48
    POSITIVE LOGITS
    onViewCreated
    0.57
     ioutil
    0.53
    исленность
    0.52
     Erde
    0.48
    Merhaba
    0.45
    หวัด
    0.44
     समीक्षक
    0.44
    Ahoj
    0.44
     TextEditing
    0.44
    initComponents
    0.43
    Activations Density 1.772%

    No Known Activations