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. 14594
    Prev
    Next
    INDEX
    Explanations

    citations in the text

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    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
     O
    -0.45
    bonucle
    -0.45
    </em>
    -0.43
    endpush
    -0.41
     S
    -0.41
     guste
    -0.40
     .
    -0.39
     hacerte
    -0.39
     V
    -0.39
     mo
    -0.38
    POSITIVE LOGITS
    abestanden
    0.91
    GEBURTSDATUM
    0.83
     utafitiHapana
    0.80
    TagMode
    0.79
    Hochspringen
    0.76
     يتيمه
    0.73
     unſ
    0.73
    ſelf
    0.73
     Efq
    0.73
    ſelves
    0.72
    Activations Density 0.876%

    No Known Activations