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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 10972
    Prev
    Next
    INDEX
    Explanations

    text from technical documents that contains attributes, measurements and specifications

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "make"

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

    make

    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
     للمعارف
    -0.52
    lanır
    -0.47
     EdgeInsets
    -0.46
    oredCriteria
    -0.43
    Portail
    -0.43
     Paglinawan
    -0.42
    +:+
    -0.42
     olympique
    -0.41
     insuffisamment
    -0.41
    NotBe
    -0.41
    POSITIVE LOGITS
     making
    2.59
     make
    2.53
     makes
    2.47
     Making
    2.45
    make
    2.41
    Making
    2.41
     Make
    2.33
    Make
    2.31
    making
    2.31
    makes
    2.28
    Activations Density 2.404%

    No Known Activations