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. 10948
    Prev
    Next
    INDEX
    Explanations

    words related to Hindu religious concepts and practices

    oai_token-act-pair · gemini-2.0-flash

    terms related to programming or technical concepts

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

    Religious rituals and Sanskrit

    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
    UnsafeEnabled
    -0.59
     Wikiseite
    -0.58
    BufferException
    -0.57
    protoimpl
    -0.56
     بيها
    -0.50
     bege
    -0.50
     defaultstate
    -0.50
     referrerpolicy
    -0.50
    يميديا
    -0.50
     hende
    -0.49
    POSITIVE LOGITS
    Notae
    0.49
    InjectAttribute
    0.48
    huahua
    0.45
     صوتيه
    0.45
    RegressionTest
    0.44
    CreateIndex
    0.44
    AssignableFrom
    0.44
    GORITH
    0.43
     Exer
    0.43
     StatefulWidget
    0.43
    Activations Density 0.593%

    No Known Activations