© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11640
    Prev
    Next
    INDEX
    Explanations

    the word "multi" and words that commonly occur with "multi"

    oai_token-act-pair · gemini-2.0-flash

    multi

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     nouveau
    -0.67
    NORE
    -0.60
    hauled
    -0.60
    -0.59
     modernize
    -0.59
     pia
    -0.59
    ventilated
    -0.57
    това
    -0.57
    -0.56
    eload
    -0.56
    POSITIVE LOGITS
    SuppressLint
    0.92
     Efq
    0.88
     GenerationType
    0.85
     photolibrary
    0.80
     Majefty
    0.78
     onAnimation
    0.77
    ſelves
    0.77
     politiet
    0.77
    ſelf
    0.75
     تانيه
    0.74
    Activations Density 1.697%

    No Known Activations