© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6662
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to Hindu worship practices and deities

    oai_token-act-pair · gemini-2.0-flash

    Hindu worship practices

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    omitempty
    -1.02
    RegressionTest
    -0.82
     архивлан
    -0.82
    MessageOf
    -0.79
    ftance
    -0.78
    oredCriteria
    -0.78
     فريبيس
    -0.77
     Efq
    -0.77
    gnition
    -0.76
     ostavi
    -0.74
    POSITIVE LOGITS
    ste
    0.39
     pri
    0.39
    alo
    0.36
    vil
    0.35
    ava
    0.35
     ENO
    0.35
     monta
    0.34
    copy
    0.34
     demek
    0.34
     blancos
    0.34
    Activations Density 0.295%

    No Known Activations