© 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. 12227
    Prev
    Next
    INDEX
    Explanations

    the word "of" preceded or followed by words such as "friend", "look" and "mine".

    oai_token-act-pair · gemini-2.0-flash

    possessive pronouns

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

    possessive pronouns

    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
     createSprite
    -0.64
     defaultstate
    -0.63
     समीक्षक
    -0.62
     iconTwitter
    -0.59
    /*
    -0.58
    PropertyChanging
    -0.57
     BoxDecoration
    -0.57
     Référence
    -0.56
    bootstrapcdn
    -0.56
    +#+
    -0.55
    POSITIVE LOGITS
    его
    0.55
     my
    0.54
     its
    0.52
    Diwedd
    0.51
    DEVICES
    0.50
    meu
    0.49
     своей
    0.49
     meu
    0.49
     ihren
    0.48
    Seu
    0.48
    Activations Density 5.344%

    No Known Activations