© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12761
    Prev
    Next
    INDEX
    Explanations

    words connected to "favor" or "honor"

    oai_token-act-pair · gemini-2.0-flash

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    θρώ
    -0.61
    UnusedPrivate
    -0.59
    Unlimited
    -0.57
    }));
    -0.56
    CodeAttribute
    -0.56
    Paradise
    -0.55
    AntiForgeryToken
    -0.54
    drawSprites
    -0.54
    以上就是
    -0.54
    XmlSchema
    -0.54
    POSITIVE LOGITS
     متعلقه
    0.67
    favor
    0.60
    Története
    0.59
    ActionCreators
    0.57
     favor
    0.57
     favors
    0.55
     FAVOR
    0.54
     Favor
    0.54
    SBATCH
    0.54
    脚注の使い方
    0.53
    Activations Density 1.017%

    No Known Activations