© 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. 13960
    Prev
    Next
    INDEX
    Explanations

    words related to religion and family

    oai_token-act-pair · gemini-2.0-flash

    Religious or familial references

    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
    <bos>
    -1.10
    DispatchToProps
    -0.64
    BagConstraints
    -0.59
    SQLException
    -0.57
    createTextNode
    -0.53
    '
    -0.51
    herz
    -0.50
    BufferException
    -0.50
    izer
    -0.49
     I
    -0.49
    POSITIVE LOGITS
     invokingState
    0.63
     kasarigan
    0.63
     tartalomajánló
    0.62
    ">)</
    0.62
    "]),
    0.61
    ">//
    0.60
    "]).
    0.60
    Hauptartikel
    0.59
    hyrchwyd
    0.59
     '*':
    0.59
    Activations Density 1.231%

    No Known Activations