© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 4800
    Prev
    Next
    INDEX
    Explanations

    the word 'each' in the context of relationships

    oai_token-act-pair · gemini-2.0-flash

    instances of the word 'each'

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

    comparison between two entities

    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
     one
    -0.60
     besides
    -0.49
    pédie
    -0.48
    alace
    -0.46
    Eloquent
    -0.45
    String
    -0.44
    داری
    -0.44
    Regi
    -0.44
     R
    -0.43
     ser
    -0.43
    POSITIVE LOGITS
    TagMode
    0.84
     Monfieur
    0.78
     Савезне
    0.74
    IntoConstraints
    0.73
    Czytaj
    0.72
    errHandler
    0.71
    styleType
    0.70
     CreateTagHelper
    0.70
     ſeveral
    0.69
     Theſe
    0.69
    Activations Density 0.187%

    No Known Activations