© 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. 37
    Prev
    Next
    INDEX
    Explanations

    a wide range of common words and phrases, but especially those expressing a state of being, existence, or condition.

    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
    Geplaatst
    -0.91
     Савезне
    -0.70
    :✨
    -0.66
    expandindo
    -0.66
    UnsafeEnabled
    -0.62
     tartalomajánló
    -0.62
    出版年
    -0.62
    setVerticalGroup
    -0.59
    \{\\
    -0.57
     referenties
    -0.57
    POSITIVE LOGITS
     defaultstate
    0.60
     javax
    0.52
     GenerationType
    0.49
    âni
    0.47
    uksen
    0.46
     tabl
    0.46
     Gari
    0.45
    weld
    0.43
    goog
    0.43
    baric
    0.42
    Activations Density 5.104%

    No Known Activations