© 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. 16095
    Prev
    Next
    INDEX
    Explanations

    comparative words and phrases

    oai_token-act-pair · gemini-2.0-flash

    more/most

    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
    UserScript
    -0.77
     sweeter
    -0.57
    avelin
    -0.57
    DrawerToggle
    -0.57
    ποτε
    -0.55
    modb
    -0.54
    ticle
    -0.53
    Superview
    -0.52
     brighter
    -0.52
     cleaner
    -0.51
    POSITIVE LOGITS
    expandindo
    0.75
    verwijspagina
    0.65
    المكان
    0.65
     متعلقه
    0.62
    __*/
    0.57
     **/
    0.57
    :✨
    0.55
    Népesség
    0.55
     }}"></
    0.55
    SourceChecksum
    0.54
    Activations Density 2.518%

    No Known Activations