© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14901
    Prev
    Next
    INDEX
    Explanations

    lists of ingredients, especially agricultural.

    oai_token-act-pair · gemini-2.0-flash

    food ingredients

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    +#+#
    -0.83
     المعيارى
    -0.82
    SourceChecksum
    -0.75
    TintMode
    -0.74
     InputDecoration
    -0.70
    Портал
    -0.69
     الدولى
    -0.69
    HasAnnotation
    -0.69
     صوتيه
    -0.69
    Portály
    -0.68
    POSITIVE LOGITS
     distill
    0.51
    MLLoader
    0.45
    олові
    0.45
    adal
    0.45
     pil
    0.41
    buttonBar
    0.41
     hoch
    0.41
     Nik
    0.41
    marathon
    0.40
    trino
    0.40
    Activations Density 1.666%

    No Known Activations