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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13526
    Prev
    Next
    INDEX
    Explanations

    names and signatures at the beginning or end of texts

    oai_token-act-pair · gemini-2.0-flash

    Names in email/messages

    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
     يتيمه
    -0.80
    encodeWith
    -0.68
    LEncoder
    -0.57
    таратура
    -0.57
     Waray
    -0.57
    ########.
    -0.56
    ecap
    -0.53
    сятся
    -0.53
    Aiheesta
    -0.53
     thun
    -0.52
    POSITIVE LOGITS
     kasarigan
    0.62
    Hentet
    0.55
    dialement
    0.53
     незавершена
    0.51
    ParallelGroup
    0.46
    endphp
    0.46
    tvguidetime
    0.44
    例文帳に追加
    0.43
    ↵↵
    0.43
    Attached
    0.43
    Activations Density 0.260%

    No Known Activations