© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10778
    Prev
    Next
    INDEX
    Explanations

    legal terms and alleged illegal activity.

    oai_token-act-pair · gemini-2.0-flash

    allegations and investigations

    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
    GraphicsUnit
    -0.63
     betweenstory
    -0.63
    ChildScrollView
    -0.60
    IntoConstraints
    -0.59
     Italijanski
    -0.56
     oprot
    -0.55
    KommentareTeilen
    -0.54
    tagext
    -0.51
    PYX
    -0.50
     сама
    -0.49
    POSITIVE LOGITS
     ISNI
    0.54
    expandindo
    0.53
     ")";
    0.50
     Hotspur
    0.50
     Passover
    0.49
     fince
    0.49
     Israelites
    0.49
     Lippincott
    0.48
     Beſ
    0.48
    ologists
    0.48
    Activations Density 2.682%

    No Known Activations