© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2739
    Prev
    Next
    INDEX
    Explanations

    code snippets, function names, and object methods, especially those including "to" and "value."

    oai_token-act-pair · gemini-2.0-flash

    method calls and type assertions

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

    Code and programming context

    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
     to
    -1.25
     propOrder
    -0.68
    withIdentifier
    -0.68
    to
    -0.59
     To
    -0.59
    SpringBootTest
    -0.57
    Спасылкі
    -0.57
    To
    -0.57
     aDecoder
    -0.57
     TO
    -0.56
    POSITIVE LOGITS
    Hochspringen
    0.59
     通販
    0.57
    ]--;
    0.52
    Skocz
    0.49
    StrictEqual
    0.47
    ंदीखरीदारी
    0.47
    sea
    0.47
    fano
    0.47
     '.';
    0.46
    AccessorTable
    0.46
    Activations Density 2.467%

    No Known Activations