© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4820
    Prev
    Next
    INDEX
    Explanations

    the word "well" and commonly collocated terms

    oai_token-act-pair · gemini-2.0-flash

    well

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     religieuses
    -0.51
     industriel
    -0.46
     pasos
    -0.41
     ~
    -0.40
    odo
    -0.38
    Released
    -0.38
    -~
    -0.38
    persist
    -0.37
    .~
    -0.37
    *~*~
    -0.37
    POSITIVE LOGITS
     resourceCulture
    0.85
    ArgsConstructor
    0.83
     CURIAM
    0.80
     AssemblyTitle
    0.80
     الحره
    0.77
     للمعارف
    0.77
     unknownFields
    0.75
     rospy
    0.73
    FunctionFlags
    0.73
    THISDAY
    0.73
    Activations Density 0.382%

    No Known Activations