© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35540
    Prev
    Next
    INDEX
    Explanations

    crisis de-escalation and safety

    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_31_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
     whip
    0.46
    鞭
    0.41
     whips
    0.41
     Whip
    0.40
     whipping
    0.39
     punishment
    0.37
     पिटाई
    0.36
     الضرب
    0.36
     सेशन
    0.35
     لطف
    0.35
    POSITIVE LOGITS
    ët
    0.38
    biod
    0.37
    喪
    0.37
    letscher
    0.36
     biliary
    0.36
     alkoh
    0.36
     chiefs
    0.35
    ubo
    0.35
     zabezpie
    0.35
     chev
    0.34
    Activations Density 0.023%

    No Known Activations