© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7215
    Prev
    Next
    INDEX
    Explanations

    text discussing the basis of authority for religious doctrines, specifically referencing religious texts

    oai_token-act-pair · gemini-2.0-flash

    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_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
    Negative Logits
     ***!
    -0.65
     Holy
    -0.64
    Holy
    -0.62
     verse
    -0.55
    בור
    -0.51
    HOLY
    -0.51
     transc
    -0.50
    holdet
    -0.47
    rü
    -0.47
     rhestr
    -0.47
    POSITIVE LOGITS
     SwitchCompat
    0.66
     commentaire
    0.65
    KeySpec
    0.63
     comentário
    0.62
    Coment
    0.61
     dog
    0.60
    脚注の使い方
    0.59
    دانشنامهٔ
    0.59
    }$​
    0.59
    dog
    0.58
    Activations Density 2.740%

    No Known Activations