Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5750
    Prev
    Next
    INDEX
    Explanations

    text about oil wells

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to well maintenance

    np_token-act-pair-logits · gpt-4o-mini

    Oil and gas extraction

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    principalColumn
    -0.59
     الحره
    -0.58
    ReusableCell
    -0.57
     LayoutInflater
    -0.54
     jspb
    -0.53
    lorette
    -0.52
     masturb
    -0.52
     समीक्षक
    -0.51
     monto
    -0.49
    riae
    -0.49
    POSITIVE LOGITS
    الحياه
    0.58
    ISupport
    0.55
     formation
    0.54
     utafitiHapana
    0.54
    ίνη
    0.54
     well
    0.52
     تضيفلها
    0.51
     reservoir
    0.50
    Inggris
    0.50
    AndroidJUnit
    0.50
    Activations Density 3.377%

    No Known Activations