© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13812
    Prev
    Next
    INDEX
    Explanations

    mentions of "subject", "issue," or reference to a document

    oai_token-act-pair · gemini-2.0-flash

    subject

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    tvguidetime
    -0.92
    addCriterion
    -0.85
    
    -0.82
     protoimpl
    -0.81
     صوتيه
    -0.79
    IsMutable
    -0.78
    photobucket
    -0.76
    tagHelperRunner
    -0.75
    :✨
    -0.75
    IsContent
    -0.74
    POSITIVE LOGITS
    <bos>
    0.66
     contras
    0.45
    Topic
    0.44
     regarding
    0.44
     موضوع
    0.42
    Lane
    0.41
     topic
    0.40
     question
    0.40
     about
    0.39
     Topic
    0.39
    Activations Density 1.440%

    No Known Activations