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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1100
    Prev
    Next
    INDEX
    Explanations

    the topic of newspapers and news archives

    oai_token-act-pair · gemini-2.0-flash

    microfilm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    <bos>
    -0.48
     ge
    -0.44
     nakalista
    -0.43
     об
    -0.43
     Kal
    -0.41
    Controllo
    -0.41
     pen
    -0.40
    Bakgrunnsstoff
    -0.40
    ex
    -0.39
     about
    -0.39
    POSITIVE LOGITS
    warded
    0.68
     متعلقه
    0.67
    Compli
    0.66
    SequentialGroup
    0.66
     ROE
    0.64
     setPrice
    0.64
    ressee
    0.62
     misuse
    0.61
     Constitucional
    0.60
    eamento
    0.59
    Activations Density 0.518%

    No Known Activations