© 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. 6076
    Prev
    Next
    INDEX
    Explanations

    words related to scientific research and technical texts

    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
     lives
    -0.84
     rents
    -0.75
     posts
    -0.74
     Lives
    -0.73
     LIVES
    -0.73
     hands
    -0.72
     disp
    -0.71
     Shares
    -0.68
     returns
    -0.67
    Lives
    -0.67
    POSITIVE LOGITS
     ModelExpression
    0.71
    FailureListener
    0.64
    UnusedPrivate
    0.55
    invokeLater
    0.54
    GeoNames
    0.54
    Datuak
    0.54
    Rhestr
    0.53
    ̍
    0.51
     يتيمه
    0.50
    Initializable
    0.50
    Activations Density 7.129%

    No Known Activations