© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4437
    Prev
    Next
    INDEX
    Explanations

    uses of the word "this" and announcements

    oai_token-act-pair · gemini-2.0-flash

    Code, research, and technical

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    omen
    -0.39
    խ
    -0.35
    men
    -0.35
    fgets
    -0.35
     who
    -0.35
     back
    -0.35
     [*]
    -0.34
    ine
    -0.34
    říklad
    -0.34
    uhn
    -0.33
    POSITIVE LOGITS
     it
    1.49
     это
    1.22
     đây
    1.13
     It
    1.03
    It
    1.02
     Đây
    1.01
     Đó
    0.97
     Это
    0.95
    这是
    0.94
    Это
    0.93
    Activations Density 1.561%

    No Known Activations