© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229036
    Prev
    Next
    INDEX
    Explanations

    culture superiority

    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_6_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
    harth
    0.94
    รรม
    0.88
     meriye
    0.85
    ה
    0.84
     EMU
    0.82
     empower
    0.82
     malonyl
    0.82
     defocus
    0.81
    ضة
    0.81
    коли
    0.81
    POSITIVE LOGITS
    ens
    1.20
    ion
    1.06
    í
    1.06
    ong
    1.05
    á
    1.05
    iv
    1.02
    ė
    1.02
    ala
    1.01
    io
    1.00
    up
    1.00
    Activations Density 0.004%

    No Known Activations