© 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. 2776
    Prev
    Next
    INDEX
    Explanations

    angle brackets and code

    oai_token-act-pair · gemini-2.0-flash

    programming syntax elements

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

    code

    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
    bootstrapcdn
    -0.55
    AntiForgeryToken
    -0.48
    ChildScrollView
    -0.45
    примеча
    -0.41
     bullion
    -0.41
     umana
    -0.39
     cabaret
    -0.39
    nskap
    -0.39
     rosary
    -0.39
     espiritual
    -0.38
    POSITIVE LOGITS
    enumi
    0.69
     dipa
    0.62
    enumii
    0.60
    door
    0.58
     Nadu
    0.58
    Portale
    0.57
    geslacht
    0.56
    writeFieldEnd
    0.56
    تقاوى
    0.56
    transQ
    0.56
    Activations Density 1.182%

    No Known Activations