© 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. 8477
    Prev
    Next
    INDEX
    Explanations

    sentences that express surprise or wonder

    oai_token-act-pair · gemini-2.0-flash

    technical or programming-related terms

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

    at

    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
     NEC
    -0.48
    del
    -0.46
    ref
    -0.42
    dom
    -0.42
     ref
    -0.41
     medi
    -0.39
     ché
    -0.38
    k
    -0.37
    重
    -0.36
    彼は
    -0.36
    POSITIVE LOGITS
     how
    1.34
    MessageTagHelper
    1.14
     فريبيس
    1.04
     صوتيه
    1.01
    IUrlHelper
    0.98
     its
    0.93
     '\\;'
    0.93
    LabelTagHelper
    0.92
     BoxFit
    0.91
    ContentAlignment
    0.90
    Activations Density 6.465%

    No Known Activations