© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9850
    Prev
    Next
    INDEX
    Explanations

    configurations or credentials related to logins and servers

    oai_token-act-pair · gemini-2.0-flash

    Authentication

    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
    urlpatterns
    -0.65
    MigrationBuilder
    -0.62
    PageRoute
    -0.59
    NameInMap
    -0.58
    getLogger
    -0.57
     AttributeSet
    -0.56
    wpi
    -0.55
    BindView
    -0.55
     Ing
    -0.54
     ویکی‌پدیا
    -0.52
    POSITIVE LOGITS
     purpoſe
    0.52
    multi
    0.51
    LEncoder
    0.51
    المشاركات
    0.50
    ykjav
    0.48
    σιμοποι
    0.47
    EDEFAULT
    0.46
    Soorten
    0.46
    Multi
    0.45
     Guter
    0.45
    Activations Density 0.873%

    No Known Activations