© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5453
    Prev
    Next
    INDEX
    Explanations

    words with a somewhat technical or legal tone, as well as sports related words and numbers when quantifying a statement

    oai_token-act-pair · gemini-2.0-flash

    technology, businesses, travel

    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
     pouvoirs
    -0.85
     épaules
    -0.85
     touristes
    -0.81
     nuages
    -0.73
     prochaines
    -0.72
     lèvres
    -0.71
     vœux
    -0.70
     genoux
    -0.70
     peuples
    -0.69
     oreilles
    -0.69
    POSITIVE LOGITS
    OGND
    0.93
    NOPQRST
    0.92
     removals
    0.88
    KURZBESCHREIBUNG
    0.85
     تضيفلها
    0.84
    Autoritní
    0.84
     beginnetje
    0.83
     conversions
    0.81
     referenties
    0.81
    styleType
    0.80
    Activations Density 23.300%

    No Known Activations