© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3257
    Prev
    Next
    INDEX
    Explanations

    references to books of the Bible

    oai_token-act-pair · gemini-2.0-flash

    Bible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ILayout
    -0.55
     forKey
    -0.53
    setDo
    -0.48
     forState
    -0.47
    amaño
    -0.47
    ữa
    -0.45
    ('@
    -0.45
    queryInterface
    -0.44
     Ansch
    -0.44
    docx
    -0.43
    POSITIVE LOGITS
    mybatisplus
    0.72
     محفوظة
    0.63
    */;
    0.59
    GOTREF
    0.58
    țională
    0.57
    олові
    0.56
     useAppContext
    0.55
    enerys
    0.54
    Tikang
    0.54
    setVerticalGroup
    0.54
    Activations Density 0.496%

    No Known Activations