© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14064
    Prev
    Next
    INDEX
    Explanations

    various pronouns or auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    words for "is"

    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
    setVerticalGroup
    -1.00
     EconPapers
    -0.99
    viewDidLoad
    -0.82
     AttributeSet
    -0.82
    ]--;
    -0.77
    FieldBuilder
    -0.73
     CURIAM
    -0.72
     faſt
    -0.71
    stateProvider
    -0.71
     resourceCulture
    -0.70
    POSITIVE LOGITS
     is
    1.33
     are
    1.04
     είναι
    0.79
     está
    0.71
     är
    0.66
     êtes
    0.65
     was
    0.64
    are
    0.62
     adalah
    0.62
     sont
    0.61
    Activations Density 2.914%

    No Known Activations