© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12245
    Prev
    Next
    INDEX
    Explanations

    code syntax and math symbols

    oai_token-act-pair · gemini-2.0-flash

    catch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    RenderAtEndOf
    -0.88
     createSlice
    -0.73
     يتيمه
    -0.73
    Havolalar
    -0.72
     kasarigan
    -0.67
     BoxDecoration
    -0.66
    Kariera
    -0.65
     AssemblyTitle
    -0.65
     ProtoMessage
    -0.65
    niker
    -0.64
    POSITIVE LOGITS
     Draw
    0.68
    withIdentifier
    0.65
     draw
    0.64
    ~•
    0.60
    ropoda
    0.57
     DRAW
    0.56
    +"'
    0.54
    SerializedSize
    0.54
     "..\..\
    0.53
     drawing
    0.52
    Activations Density 1.929%

    No Known Activations