© 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-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5414
    Prev
    Next
    INDEX
    Explanations

    truth and related concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_38_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trimming
    0.38
    glichkeiten
    0.38
     اسٹی
    0.38
    trif
    0.37
    嚓
    0.37
     epidemi
    0.37
     counselor
    0.36
     comparaison
    0.36
     Epidemi
    0.36
     comparison
    0.35
    POSITIVE LOGITS
     Truth
    0.61
    Truth
    0.60
    truth
    0.59
     truth
    0.58
     सत्य
    0.51
     truths
    0.46
     truthful
    0.45
     прав
    0.44
     praw
    0.44
     真
    0.42
    Activations Density 0.014%

    No Known Activations