© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16170
    Prev
    Next
    INDEX
    Explanations

    labels or captions, especially those associated with figures or numerical data

    oai_token-act-pair · gemini-2.0-flash

    colors

    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
    AutoScale
    -0.56
     تضيفلها
    -0.53
    pierw
    -0.49
     verdieping
    -0.48
    Хьажоргаш
    -0.48
     kasarigan
    -0.47
     FetchType
    -0.47
     orar
    -0.47
    mainAxisSize
    -0.47
    GeoNames
    -0.46
    POSITIVE LOGITS
     Black
    1.56
     Red
    1.55
     Blue
    1.44
     White
    1.39
     Green
    1.35
    Black
    1.33
    Red
    1.32
     Yellow
    1.25
    Blue
    1.22
    White
    1.16
    Activations Density 8.073%

    No Known Activations