© 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. 5811
    Prev
    Next
    INDEX
    Explanations

    various forms of user feedback, technical software jargon, and cleaning product names

    oai_token-act-pair · gemini-2.0-flash

    Document sections

    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
     advanced
    -0.66
     proactive
    -0.64
     enhanced
    -0.59
     higher
    -0.57
    advanced
    -0.57
     effective
    -0.57
     premature
    -0.57
     zengin
    -0.56
     secure
    -0.56
     high
    -0.55
    POSITIVE LOGITS
     song
    0.92
     column
    0.91
     section
    0.88
     scheme
    0.88
     page
    0.88
     box
    0.88
     sheet
    0.87
     table
    0.87
     article
    0.86
     project
    0.85
    Activations Density 12.667%

    No Known Activations