© 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. 12277
    Prev
    Next
    INDEX
    Explanations

    lines that are not actual content, e.g. formatting or reference markers

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    consulté
    -0.65
     ویکی‌پدیای
    -0.60
    fjspx
    -0.59
    abestanden
    -0.58
    ineno
    -0.58
    writeFieldEnd
    -0.57
    日閲覧
    -0.57
     po
    -0.56
    tvguidetime
    -0.52
    +#+
    -0.50
    POSITIVE LOGITS
     Morena
    0.58
    ecé
    0.57
    dagangan
    0.57
     Melhor
    0.57
     ComVisible
    0.54
     souten
    0.54
    synonyms
    0.54
    LEEP
    0.54
    economics
    0.54
     joyeux
    0.53
    Activations Density 1.252%

    No Known Activations