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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1120
    Prev
    Next
    INDEX
    Explanations

    OpenCV code for image processing

    oai_token-act-pair · gemini-2.0-flash

    code/programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Signalez
    -0.94
     podjela
    -0.76
    AddTagHelper
    -0.71
     AssemblyVersion
    -0.71
     Av
    -0.68
     ostavi
    -0.66
    NV
    -0.65
    RenderAtEndOf
    -0.65
    Av
    -0.65
     Савезне
    -0.65
    POSITIVE LOGITS
    omenclature
    0.48
    PutMapping
    0.45
    chdir
    0.43
     asiática
    0.43
     conda
    0.41
    kranz
    0.41
    kernels
    0.41
     Mexicano
    0.41
    plotly
    0.40
    inata
    0.40
    Activations Density 4.666%

    No Known Activations