© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5863
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word take

    oai_token-act-pair · gemini-2.0-flash

    take

    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
    homonymie
    -0.57
     resourceCulture
    -0.57
     bpy
    -0.51
     незавершена
    -0.50
     ra
    -0.46
    hObject
    -0.46
    UNIC
    -0.45
    Martes
    -0.45
       
    -0.44
     Kul
    -0.43
    POSITIVE LOGITS
    NameInMap
    0.86
    yntaxException
    0.69
     TestBed
    0.67
    TestBed
    0.66
    fjspx
    0.59
    SpringBoot
    0.58
     Վերցված
    0.57
    UnsafeEnabled
    0.56
     mxArray
    0.56
     للاسماء
    0.55
    Activations Density 0.386%

    No Known Activations