© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12613
    Prev
    Next
    INDEX
    Explanations

    phrases discussing conflict and obstacles

    oai_token-act-pair · gemini-2.0-flash

    words related to barriers or constraints

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

    barriers

    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
    <bos>
    -0.69
     intptr
    -0.66
     CreateTagHelper
    -0.66
    ✨:
    -0.62
    addPreferredGap
    -0.57
    abestanden
    -0.54
    
    -0.53
    पया
    -0.52
    eaways
    -0.48
    ГЛА
    -0.48
    POSITIVE LOGITS
     wires
    0.68
     tape
    0.65
     ropes
    0.63
    wires
    0.63
     wire
    0.60
     barbed
    0.60
     Wikimedijinoj
    0.58
     tapes
    0.57
    sprozess
    0.57
     red
    0.55
    Activations Density 1.332%

    No Known Activations