© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5192
    Prev
    Next
    INDEX
    Explanations

    the word "boy"

    oai_token-act-pair · gemini-2.0-flash

    boy

    np_max-act · gemini-2.0-flash

    boy

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     boys
    -2.73
     boy
    -2.55
     Boys
    -2.52
    Boys
    -2.50
    boys
    -2.48
     BOYS
    -2.34
    boy
    -2.19
     Boy
    -2.17
    BOYS
    -2.13
    Boy
    -2.09
    POSITIVE LOGITS
    formik
    0.55
    JsonHelper
    0.54
    녕
    0.53
     inggris
    0.52
     UnityEngine
    0.49
    IBU
    0.49
    Daughter
    0.49
    lementation
    0.49
    ResponseWriter
    0.48
    undu
    0.47
    Activations Density 0.349%

    No Known Activations