© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5844
    Prev
    Next
    INDEX
    Explanations

    references to God, Jesus, or the Bible.

    oai_token-act-pair · gemini-2.0-flash

    Religious/Biblical 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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    Portale
    -0.79
    XmlEnum
    -0.76
    XmlAccessType
    -0.73
    stateMutability
    -0.73
    脚注の使い方
    -0.71
    Datuak
    -0.70
     Signalez
    -0.70
    PreferredItem
    -0.68
    SourceChecksum
    -0.68
    StoryboardSegue
    -0.67
    POSITIVE LOGITS
    совая
    0.41
    ব
    0.38
    ト
    0.38
     szinte
    0.38
     top
    0.37
     déplacer
    0.37
    ignan
    0.36
     T
    0.36
     mo
    0.36
     höchsten
    0.36
    Activations Density 2.030%

    No Known Activations