© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236153
    Prev
    Next
    INDEX
    Explanations

    punishable

    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_32_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
     anger
    0.42
    罪
    0.41
     imposition
    0.38
     scolded
    0.37
    criminal
    0.36
     criminal
    0.36
    罵
    0.36
     গাড়িতে
    0.36
     blamed
    0.36
    LineEdit
    0.36
    POSITIVE LOGITS
     Referring
    0.36
    挫
    0.34
     Referral
    0.34
     disprove
    0.32
     المحلي
    0.32
     Client
    0.32
     REFER
    0.32
     dispers
    0.31
     পুনরুদ্ধ
    0.31
     CLIENT
    0.31
    Activations Density 0.004%

    No Known Activations