© 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. 13118
    Prev
    Next
    INDEX
    Explanations

    mentions of specific people, places, and things, especially when associated with narratives or storytelling

    oai_token-act-pair · gemini-2.0-flash

    specific tokens or terms from technical or programming contexts

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

    Extracted text from books

    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
     she
    -3.44
     her
    -2.89
    she
    -2.73
    She
    -2.45
     hers
    -2.38
     그녀
    -2.33
    彼女の
    -2.30
     shes
    -2.19
     She
    -2.14
    她
    -2.14
    POSITIVE LOGITS
    CloseOperation
    0.80
    ньому
    0.76
     okuyayım
    0.70
     celui
    0.64
     him
    0.64
    JspWriter
    0.61
     esso
    0.60
     endblock
    0.60
     raiſ
    0.60
     getItemCount
    0.59
    Activations Density 4.916%

    No Known Activations