© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11217
    Prev
    Next
    INDEX
    Explanations

    words related to offerings, provisions, or bestowing

    oai_token-act-pair · gemini-2.0-flash

    providing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    Personendaten
    -0.82
    ⓧ
    -0.66
     MotionEvent
    -0.61
    AxisAlignment
    -0.60
    verwijspagina
    -0.58
    الدراسه
    -0.56
    InjectAttribute
    -0.56
     ujednoznacz
    -0.56
    IndentedString
    -0.56
     residency
    -0.55
    POSITIVE LOGITS
    jarkan
    0.58
    ContentAsync
    0.57
    ngrx
    0.53
    ếu
    0.52
     transmits
    0.50
     dụ
    0.50
    ให้
    0.49
     preparada
    0.49
    UseVisualStyle
    0.48
    ADELPHIA
    0.48
    Activations Density 2.678%

    No Known Activations