© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4932
    Prev
    Next
    INDEX
    Explanations

    capitalized single letters on their own or preceding text

    oai_token-act-pair · gemini-2.0-flash

    identifiers and attributes in programming contexts

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

    programming names/places

    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
     kasarigan
    -0.64
     sols
    -0.61
    numerusform
    -0.60
    mism
    -0.57
    íncia
    -0.57
     ordinario
    -0.56
    帖最后由
    -0.56
     kingdoms
    -0.51
     Himo
    -0.51
     banger
    -0.51
    POSITIVE LOGITS
     AssemblyTitle
    0.55
     dataSnapshot
    0.54
    ">//
    0.51
    >>()
    0.48
    stateProvider
    0.47
    ImageContext
    0.47
     ujednoznacz
    0.46
    providedIn
    0.46
    oh
    0.44
     الحره
    0.44
    Activations Density 0.411%

    No Known Activations