© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12293
    Prev
    Next
    INDEX
    Explanations

    the letter "W" preceded by a space and often followed by a period or other letters

    oai_token-act-pair · gemini-2.0-flash

    W

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     />);
    -0.60
     stá
    -0.57
    toFloat
    -0.56
    assertSame
    -0.54
    monary
    -0.51
    FailureListener
    -0.50
     Aseg
    -0.50
    YTICAL
    -0.50
     yến
    -0.49
     samfun
    -0.49
    POSITIVE LOGITS
    tagHelperRunner
    0.57
    èdia
    0.52
     للمعارف
    0.48
     iprot
    0.47
    atik
    0.47
    SharedCtor
    0.46
    MOC
    0.46
    sidemargin
    0.44
    culares
    0.43
     Мексичка
    0.43
    Activations Density 0.707%

    No Known Activations