© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211763
    Prev
    Next
    INDEX
    Explanations

    opposed, opposes, oppressed

    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_5_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
    ä
    1.34
    ل
    1.33
    л
    1.16
     It
    1.07
    ح
    1.01
    ма
    0.98
    기는
    0.97
    로서
    0.96
    적으로
    0.95
    고
    0.94
    POSITIVE LOGITS
    0
    1.54
    ;
    1.25
    P
    1.19
    ন
    1.13
     weaken
    1.11
    לי
    1.10
     thicken
    1.06
     advertise
    1.05
     deceive
    1.05
     deteriorate
    1.05
    Activations Density 0.003%

    No Known Activations