© 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. 12250
    Prev
    Next
    INDEX
    Explanations

    negations and conjunctions

    oai_token-act-pair · gemini-2.0-flash

    negations and conditions

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

    not

    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
    Erreferentziak
    -0.60
     Normdatei
    -0.60
    تقاوى
    -0.59
     Roskov
    -0.59
    writeFieldEnd
    -0.57
    kegaard
    -0.57
    pgsql
    -0.57
    ValueGeneration
    -0.56
    Jereo
    -0.56
    timewa
    -0.55
    POSITIVE LOGITS
     occurring
    0.59
     pakan
    0.57
     happening
    0.56
     destined
    0.52
    <bos>
    0.48
    httphttps
    0.48
    happ
    0.48
     freely
    0.47
     riusc
    0.47
     întâ
    0.46
    Activations Density 6.882%

    No Known Activations