© 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. 14544
    Prev
    Next
    INDEX
    Explanations

    context related to scientific research and value judgements/statements.

    oai_token-act-pair · gemini-2.0-flash

    technical/scientific texts

    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
     Beyond
    -1.95
    beyond
    -1.90
     beyond
    -1.87
    Beyond
    -1.84
     BEYOND
    -1.79
     below
    -1.66
     Below
    -1.62
     exceed
    -1.59
     exceeding
    -1.57
    Below
    -1.50
    POSITIVE LOGITS
    èdia
    0.56
     InputDecoration
    0.56
    matchCondition
    0.55
    (&:
    0.54
    MessageOf
    0.53
    CodeAttribute
    0.52
    djangoproject
    0.52
     CreateTagHelper
    0.52
    Diwedd
    0.52
    libft
    0.50
    Activations Density 3.649%

    No Known Activations