© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 65651
    Prev
    Next
    INDEX
    Explanations

    ethical concerns

    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
    {-\
    0.38
     consigui
    0.38
    翕
    0.36
     overcame
    0.36
     Affect
    0.36
     CHARLES
    0.36
    㖑
    0.35
    Affect
    0.34
    Kiza
    0.34
     दिवसीय
    0.33
    POSITIVE LOGITS
     perpet
    0.46
     indeed
    0.38
    ኒ
    0.38
     ecosystems
    0.38
     continuity
    0.38
     assurance
    0.37
     estruct
    0.37
    ንዱ
    0.37
     workflow
    0.36
     shaping
    0.36
    Activations Density 0.008%

    No Known Activations