© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10958
    Prev
    Next
    INDEX
    Explanations

    ingredients used in cooking

    oai_token-act-pair · gemini-2.0-flash

    Citrus fruits

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Orange
    -1.11
     orange
    -1.05
    Orange
    -1.04
     Yellow
    -1.03
     yellow
    -1.01
     ORANGE
    -1.01
     citrus
    -0.94
    orange
    -0.92
     YELLOW
    -0.90
    Yellow
    -0.89
    POSITIVE LOGITS
     sat
    0.54
    sat
    0.47
    Sat
    0.43
     विश्वसनीयता
    0.42
     Sat
    0.41
     Савезне
    0.40
    vedo
    0.39
    letal
    0.39
    Bibliograf
    0.39
     متعلقه
    0.38
    Activations Density 1.127%

    No Known Activations