© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14703
    Prev
    Next
    INDEX
    Explanations

    the word "cap" used in a technical context

    oai_token-act-pair · gemini-2.0-flash

    cap

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -1.13
      
    -0.83
    ↵
    -0.81
    1
    -0.80
    ↵↵
    -0.80
    '
    -0.76
    <eos>
    -0.75
       
    -0.75
            
    -0.74
    2
    -0.74
    POSITIVE LOGITS
    Datuak
    1.31
    NameInMap
    1.20
    writeFieldEnd
    1.19
     المعيارى
    1.15
    存于互联网档案馆
    1.15
    providedIn
    1.11
    ]")]
    1.10
     <<<<<<<<<<<<<<
    1.09
     >=",
    1.08
    QMetaType
    1.08
    Activations Density 3.334%

    No Known Activations