© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8884
    Prev
    Next
    INDEX
    Explanations

    message headers including names, dates, and the start of message replies

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     victimes
    -0.47
     campione
    -0.46
    ejb
    -0.45
    RenderAtEndOf
    -0.45
     bâton
    -0.44
     medel
    -0.42
     paroisse
    -0.42
     vícti
    -0.42
     guste
    -0.42
     victime
    -0.41
    POSITIVE LOGITS
     utafitiHapana
    0.71
    ########.
    0.67
     allAfrica
    0.66
    الحياه
    0.62
     שוליים
    0.59
    DeleteBehavior
    0.55
     мәкал
    0.55
    хьтан
    0.55
    енча
    0.55
     <",
    0.54
    Activations Density 0.773%

    No Known Activations