© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14452
    Prev
    Next
    INDEX
    Explanations

    language related to religious expression

    oai_token-act-pair · gemini-2.0-flash

    academic/religious texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    RenderAtEndOf
    -0.64
    wpi
    -0.59
    はじめに
    -0.58
    abetes
    -0.56
     Comprometido
    -0.53
     conseillers
    -0.52
    plato
    -0.51
    StackNavigator
    -0.50
    HomeAsUpEnabled
    -0.49
     supérieurs
    -0.49
    POSITIVE LOGITS
    rungsseite
    0.70
     مرئيه
    0.68
     '\\;'
    0.61
     snippetHide
    0.60
    colhead
    0.57
    ContentAsync
    0.55
    akterysty
    0.55
    HttpPut
    0.54
     BytesLike
    0.53
    Nhan
    0.52
    Activations Density 5.984%

    No Known Activations