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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14786
    Prev
    Next
    INDEX
    Explanations

    prepositions and words describing duration or location

    oai_token-act-pair · gemini-2.0-flash

    over

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Houſe
    -0.82
     Efq
    -0.81
    "]];
    -0.76
     >",
    -0.75
    CodeAttribute
    -0.75
    rrggbb
    -0.71
     ―――――
    -0.71
     itſelf
    -0.71
     ſever
    -0.70
     houſe
    -0.70
    POSITIVE LOGITS
     chapelle
    0.48
     a
    0.47
    ENTLY
    0.46
     the
    0.44
     הכל
    0.43
    生素
    0.42
    InSection
    0.42
     Ngọc
    0.42
     and
    0.42
    plen
    0.41
    Activations Density 10.667%

    No Known Activations