© 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. 6886
    Prev
    Next
    INDEX
    Explanations

    the word "night" and words associated with it

    oai_token-act-pair · gemini-2.0-flash

    night

    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
    tagext
    -0.68
    PYX
    -0.65
    ValueGeneration
    -0.63
    WebElementEntity
    -0.59
    ContentAsync
    -0.58
    XmlAccessorType
    -0.58
    featureID
    -0.58
    تقاوى
    -0.57
    sizeCache
    -0.57
     garanzia
    -0.57
    POSITIVE LOGITS
     move
    0.56
     time
    0.51
    Hozzáférés
    0.50
     shift
    0.50
    move
    0.50
    nables
    0.49
     moves
    0.49
    orianCalendar
    0.49
    ivore
    0.47
    InSection
    0.47
    Activations Density 0.924%

    No Known Activations