© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14616
    Prev
    Next
    INDEX
    Explanations

    some form of the verb "to go" that has an adverb following it such as "went on"

    oai_token-act-pair · gemini-2.0-flash

    go

    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
    ftagPool
    -0.59
    IsContent
    -0.58
     MyBatis
    -0.54
    EndContext
    -0.53
    #
    -0.52
    wpi
    -0.50
    Cuba
    -0.50
    ScreenState
    -0.49
    ResponseWriter
    -0.49
     Riva
    -0.49
    POSITIVE LOGITS
     whoſe
    0.59
     themſelves
    0.59
    )))));
    0.58
     Theſe
    0.58
     itſelf
    0.57
     himſelf
    0.57
     houſe
    0.56
     Monfieur
    0.56
    ductory
    0.56
     Efq
    0.54
    Activations Density 0.558%

    No Known Activations