© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5915
    Prev
    Next
    INDEX
    Explanations

    code snippets, especially ones referencing PHP and file paths.

    oai_token-act-pair · 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
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.63
    тельству
    -0.56
    EndInit
    -0.54
    出版年
    -0.54
    MemoryWarning
    -0.53
    Przypisy
    -0.53
    目で
    -0.52
    GEBURTSDATUM
    -0.52
    ynb
    -0.52
    Erreferentziak
    -0.51
    POSITIVE LOGITS
    AxisAlignment
    0.57
    ellemző
    0.57
    лтамалар
    0.55
     disarm
    0.54
     Liberation
    0.54
    =$?
    0.53
    eachtet
    0.52
     becauſe
    0.52
    kloped
    0.52
     Tacitus
    0.52
    Activations Density 0.507%

    No Known Activations