© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7785
    Prev
    Next
    INDEX
    Explanations

    the word "honest" or variants of it

    oai_token-act-pair · gemini-2.0-flash

    honest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     honest
    -2.09
    honest
    -1.76
     Honest
    -1.67
    Honest
    -1.63
    <bos>
    -1.55
     honesty
    -1.51
     honestly
    -1.27
     truthful
    -1.20
     Honesty
    -1.18
     honnête
    -1.16
    POSITIVE LOGITS
    PullParser
    0.81
    EndProject
    0.76
    EndInit
    0.75
    PMailer
    0.74
    InjectAttribute
    0.72
    Tembelea
    0.71
     utafitiHapana
    0.70
    BeginInit
    0.70
    findpost
    0.70
    WaitGroup
    0.69
    Activations Density 3.089%

    No Known Activations