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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5572
    Prev
    Next
    INDEX
    Explanations

    words related to the Hindu religion or philosophy, particularly focusing on states of being and divine concepts.

    oai_token-act-pair · gemini-2.0-flash

    of

    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
    dafx
    -0.56
     fubject
    -0.55
     EconPapers
    -0.51
    ⓧ
    -0.50
    мец
    -0.49
     ویکی‌پدی
    -0.49
     """
    -0.47
     sumpay
    -0.47
    TabStop
    -0.47
     occaf
    -0.46
    POSITIVE LOGITS
    rungsseite
    0.73
     ***!
    0.56
     affirmation
    0.50
    tedly
    0.50
     thoughtless
    0.50
    SMC
    0.50
     Bergmann
    0.49
     dynamism
    0.49
     Jaffe
    0.49
    erequisite
    0.49
    Activations Density 15.062%

    No Known Activations