© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5572
    Prev
    Next
    INDEX
    Explanations

    food recipe steps and ingredients, especially citrus

    oai_token-act-pair · gemini-2.0-flash

    lemon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    tagHelperRunner
    -0.84
     considérons
    -0.73
     للمعارف
    -0.73
    postsleuth
    -0.70
    abestanden
    -0.69
    tvguidetime
    -0.69
    kegaard
    -0.68
    enderror
    -0.67
     MonoBehaviour
    -0.66
    Населення
    -0.65
    POSITIVE LOGITS
    zula
    0.47
     minh
    0.45
     full
    0.44
    vot
    0.42
     half
    0.42
     rating
    0.42
    piegel
    0.40
     اب
    0.39
    ocr
    0.39
     word
    0.39
    Activations Density 1.888%

    No Known Activations