© 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. 5591
    Prev
    Next
    INDEX
    Explanations

    language referring to the recent past and time

    oai_token-act-pair · gemini-2.0-flash

    indicators related to updates and previous content

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

    update announcements

    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
     dovuto
    -0.46
     ragioni
    -0.40
     espejo
    -0.40
    pos
    -0.39
     которым
    -0.38
    DropColumn
    -0.38
     jouets
    -0.37
     Wikimedijinoj
    -0.36
    sill
    -0.35
     sconfit
    -0.35
    POSITIVE LOGITS
    IsContent
    0.78
     betweenstory
    0.76
    
    0.76
    ViewFeatures
    0.73
    IUrlHelper
    0.70
    MLLoader
    0.69
     متعلقه
    0.68
     greateſt
    0.68
     "..\..\
    0.67
     mention
    0.66
    Activations Density 3.378%

    No Known Activations