© 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. 12613
    Prev
    Next
    INDEX
    Explanations

    words describing family relationships

    oai_token-act-pair · gemini-2.0-flash

    family

    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
     Penetration
    -0.50
    jala
    -0.48
    영화
    -0.48
    ATTR
    -0.46
     penetration
    -0.45
    Biographie
    -0.45
    стати
    -0.44
    níky
    -0.44
     táo
    -0.44
    meability
    -0.44
    POSITIVE LOGITS
     تضيفلها
    0.91
    ContentAsync
    0.69
     springfox
    0.66
     <<<<<<<<<<<<<<
    0.60
    antaranya
    0.59
     iprot
    0.58
    interopRequire
    0.58
    UnusedPrivate
    0.56
    UpInside
    0.55
    UseVisualStyle
    0.54
    Activations Density 0.398%

    No Known Activations