© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5682
    Prev
    Next
    INDEX
    Explanations

    theological discussions, especially words with high religious connotations

    oai_token-act-pair · gemini-2.0-flash

    technical terms or code-related concepts

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

    Religious/Mormon afterlife

    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
     cherchés
    -0.69
     فريبيس
    -0.66
     Paglinawan
    -0.65
    таратура
    -0.57
     Ebers
    -0.57
     podjela
    -0.56
     دیکھیے
    -0.55
     estimés
    -0.55
    matchCondition
    -0.54
    ագրություններ
    -0.52
    POSITIVE LOGITS
    TagMode
    0.54
     AttributeSet
    0.48
    fopen
    0.45
     VizieR
    0.45
     ganglion
    0.44
     Bo
    0.44
    Ắ
    0.42
     Saltar
    0.42
    putAll
    0.41
    Bo
    0.41
    Activations Density 1.100%

    No Known Activations