© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13409
    Prev
    Next
    INDEX
    Explanations

    phrases containing the words "keep," "us," "publisher," or related to medical patients

    oai_token-act-pair · gemini-2.0-flash

    from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     الحره
    -0.63
     &___
    -0.62
    WriteTagHelper
    -0.59
    setArguments
    -0.56
     kasarigan
    -0.55
    complexType
    -0.53
    fjspx
    -0.51
    leville
    -0.50
    Hauptartikel
    -0.49
    \}=
    -0.48
    POSITIVE LOGITS
     from
    2.44
    from
    1.86
     FROM
    1.63
     From
    1.54
    From
    1.54
     từ
    1.52
     från
    1.51
    จาก
    1.47
    FROM
    1.42
     desde
    1.36
    Activations Density 1.324%

    No Known Activations