© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6305
    Prev
    Next
    INDEX
    Explanations

    words ending in "ing", possessive nouns, and company/organization names.

    oai_token-act-pair · gemini-2.0-flash

    motion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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>
    -0.95
    AddAttribute
    -0.50
     righe
    -0.50
    存于互联网档案馆
    -0.49
    Населення
    -0.48
     didnt
    -0.47
     sekitarnya
    -0.47
     hidupnya
    -0.47
    __':
    -0.46
    Autoritní
    -0.46
    POSITIVE LOGITS
    hamilan
    0.57
    omenclature
    0.56
     trajets
    0.54
    gros
    0.52
    elry
    0.52
     صوتيه
    0.52
    ittà
    0.51
     dow
    0.51
    WritableDatabase
    0.50
    downtown
    0.50
    Activations Density 0.733%

    No Known Activations