© 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. 9168
    Prev
    Next
    INDEX
    Explanations

    phrases that include the word "first," sometimes including the word "in" or "out," and sometimes something somewhat related to office jobs.

    oai_token-act-pair · gemini-2.0-flash

    General text

    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
     nakalista
    -0.66
    }}}}
    -0.66
    )))));
    -0.66
     ©️
    -0.65
    SuspendLayout
    -0.63
    {§
    -0.62
    UserScript
    -0.62
    "]];
    -0.60
    "]));
    -0.60
    WireFormatLite
    -0.60
    POSITIVE LOGITS
     Gutter
    0.50
     nahilalakip
    0.48
    ,
    0.47
     AssemblyProduct
    0.46
    Daz
    0.46
     CreateTagHelper
    0.45
    уза
    0.45
    Xamarin
    0.45
    mudi
    0.44
    ító
    0.44
    Activations Density 1.720%

    No Known Activations