© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15295
    Prev
    Next
    INDEX
    Explanations

    mentions of "truth" and related concepts

    oai_token-act-pair · gemini-2.0-flash

    words related to truth and honesty

    np_token-act-pair-logits · gpt-4o-mini

    truth, reality

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     planas
    -0.46
     étrangères
    -0.44
     giapp
    -0.40
     ambientales
    -0.39
     militaires
    -0.39
    ky
    -0.39
     Jerusalén
    -0.39
     tecnológicos
    -0.38
     località
    -0.38
     educativas
    -0.37
    POSITIVE LOGITS
    исленность
    0.78
    StoryboardSegue
    0.75
    basicConfig
    0.73
    RegressionTest
    0.72
    sidemargin
    0.71
    httphttps
    0.70
     насељу
    0.70
    ніципа
    0.69
    ContentAsync
    0.69
    Geplaatst
    0.69
    Activations Density 2.730%

    No Known Activations