© 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. 11548
    Prev
    Next
    INDEX
    Explanations

    code or table-like data with numbers and formatting

    oai_token-act-pair · gemini-2.0-flash

    code/tables

    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
     nahilalakip
    -0.83
     виправивши
    -0.68
    bcryptjs
    -0.60
    GeneratedMessage
    -0.56
     continúas
    -0.53
    __).
    -0.53
    MessageInfo
    -0.52
     ویکی‌پدیای
    -0.52
    featureID
    -0.52
     calendriers
    -0.52
    POSITIVE LOGITS
    apj
    0.50
     IconData
    0.49
     imageNamed
    0.48
    Besch
    0.47
     <=",
    0.46
    듭
    0.46
    ereço
    0.45
    ammans
    0.44
     Brant
    0.44
     Ile
    0.44
    Activations Density 1.013%

    No Known Activations