Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 6150
    Prev
    Next
    INDEX
    Explanations

    the string "ideas" and anything with dollar amounts, urls, dates, times, or lists

    oai_token-act-pair · gemini-2.0-flash

    terms related to video and media content

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

    Text excerpts

    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
     Mor
    -0.54
    .*;
    -0.52
    ียว
    -0.51
    őt
    -0.50
    .*;
    
    -0.50
    omir
    -0.50
    sia
    -0.49
     gav
    -0.48
     Mal
    -0.47
    ussi
    -0.47
    POSITIVE LOGITS
     مرئيه
    0.81
    ViewFeatures
    0.72
    XmlAccessType
    0.72
    ⓧ
    0.71
    AsUp
    0.69
     betweenstory
    0.66
     Wikispecies
    0.66
     المعيارى
    0.65
    ConstraintMaker
    0.60
     ModelRenderer
    0.59
    Activations Density 6.116%

    No Known Activations