© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138729
    Prev
    Next
    INDEX
    Explanations

    peace

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    ₁,
    0.41
    őt
    0.40
     malle
    0.38
    ▸
    0.38
     enquire
    0.35
     rakk
    0.35
    ₁(
    0.35
    "><!--
    0.35
    荻
    0.35
    propylene
    0.35
    POSITIVE LOGITS
     peace
    2.92
    Peace
    2.84
    peace
    2.80
     Peace
    2.77
     PEACE
    2.64
     peaceful
    2.56
    和平
    2.52
     Peaceful
    2.36
     мир
    2.31
     शांति
    2.25
    Activations Density 0.002%

    No Known Activations