© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5226
    Prev
    Next
    INDEX
    Explanations

    verbs related to the state of being, such as have, has, is, was, etc

    oai_token-act-pair · gemini-2.0-flash

    programming-related terminology and functions

    np_token-act-pair-logits · gpt-4o-mini

    have

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    ंदीखरीदारी
    -0.58
     Савезне
    -0.56
    ptonshire
    -0.54
    }],
    
    -0.52
    )),
    
    -0.50
     صوتيه
    -0.50
    "},
    
    -0.49
     referenties
    -0.49
    nodoc
    -0.48
    وأ
    -0.48
    POSITIVE LOGITS
     BorderRadius
    0.71
    ]--;
    0.64
    UnknownFields
    0.59
    StandardCharsets
    0.57
     complete
    0.57
    setArguments
    0.52
     nothing
    0.52
    ReusableCell
    0.49
    acuzzi
    0.49
    parametrize
    0.49
    Activations Density 0.757%

    No Known Activations