© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12165
    Prev
    Next
    INDEX
    Explanations

    math equations and matrix representations

    oai_token-act-pair · gemini-2.0-flash

    Code/Math expressions

    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
    Not in Any Lists

    No Comments

    Negative Logits
     IBOutlet
    -0.51
     كومونز
    -0.49
    ISupport
    -0.49
    ChildScrollView
    -0.48
     Reverso
    -0.47
    __":
    -0.47
    omitempty
    -0.47
    EUROPA
    -0.46
    FieldNumber
    -0.46
     muualla
    -0.46
    POSITIVE LOGITS
     мәкал
    0.66
    oredCriteria
    0.60
    MigrationBuilder
    0.57
    MultipartFile
    0.57
    
    0.56
    rativa
    0.55
    expandindo
    0.54
    الحياه
    0.54
    UnsafeEnabled
    0.54
    tvguidetime
    0.51
    Activations Density 0.851%

    No Known Activations