© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3392
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in restaurant reviews

    oai_token-act-pair · gemini-2.0-flash

    technical terms or jargon

    np_token-act-pair-logits · gpt-4o-mini

    Restaurant menus and dining

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    IBOutlet
    -0.53
    oliber
    -0.49
     dentelle
    -0.49
     blanches
    -0.47
     Outils
    -0.45
     maglia
    -0.44
    쁨
    -0.43
     hứng
    -0.43
    dismo
    -0.42
    kennung
    -0.42
    POSITIVE LOGITS
    fromnode
    0.61
     AssemblyCulture
    0.59
    ReusableCell
    0.57
    Autoritní
    0.54
    ̲
    0.54
     setPassword
    0.53
    reasonably
    0.51
     فہرست
    0.50
    Vidite
    0.49
    ỡng
    0.49
    Activations Density 1.297%

    No Known Activations