© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232867
    Prev
    Next
    INDEX
    Explanations

    Opium Wars

    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
     residues
    0.38
    변경
    0.37
    ointing
    0.35
    怀疑
    0.35
    TSC
    0.34
    に変更
    0.34
    tgz
    0.34
    弇
    0.34
    ServiceGroupID
    0.34
    क्तिक
    0.34
    POSITIVE LOGITS
     cannabis
    0.40
     budu
    0.38
     novella
    0.38
     Eleventh
    0.37
    演讲
    0.36
     Cannabis
    0.35
     Ninth
    0.35
     Bonus
    0.35
     буду
    0.35
     Fintech
    0.34
    Activations Density 0.001%

    No Known Activations