© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4919
    Prev
    Next
    INDEX
    Explanations

    text related to image scanning and motion artifacts

    oai_token-act-pair · gemini-2.0-flash

    experimental noise/artifacts

    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
     المعيارى
    -0.79
    Hentet
    -0.75
    WithIOException
    -0.71
    tagHelperRunner
    -0.68
     GenerationType
    -0.68
    principalColumn
    -0.67
    WaitGroup
    -0.67
    apimachinery
    -0.66
    thansa
    -0.66
     defaultstate
    -0.65
    POSITIVE LOGITS
    rios
    0.47
    ೆ
    0.47
    調
    0.46
    IsContent
    0.45
    Companion
    0.45
     Potts
    0.45
     trajectory
    0.44
     hứng
    0.44
     Draht
    0.43
    pane
    0.43
    Activations Density 9.019%

    No Known Activations