© 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. 12907
    Prev
    Next
    INDEX
    Explanations

    HTML and Javascript code related to a data grid with CRUD operations

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    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
    出版年
    -0.61
    StoryboardSegue
    -0.57
    rrggbb
    -0.55
     Preferencias
    -0.54
     Référence
    -0.49
    Rohy
    -0.47
     estekak
    -0.47
    netbeans
    -0.46
    BeforeEach
    -0.46
     Quarterly
    -0.46
    POSITIVE LOGITS
    extAlignment
    0.72
    DockStyle
    0.59
    ispo
    0.52
    NOPQRST
    0.51
     verwijzen
    0.51
    itre
    0.50
    estay
    0.49
     Alar
    0.49
    ArrowToggle
    0.48
     الدولى
    0.47
    Activations Density 6.356%

    No Known Activations