© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 212783
    Prev
    Next
    INDEX
    Explanations

    rat kings, ratemyprofessor, rat race

    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
    ible
    1.02
    ings
    0.96
    ő
    0.96
    ikh
    0.95
    కి
    0.94
    ach
    0.93
    ۰۰
    0.92
    ores
    0.90
    ized
    0.89
    ished
    0.88
    POSITIVE LOGITS
    א
    1.63
    ન
    1.20
    ک
    1.14
    ை
    1.09
    ന്‍
    1.06
    אס
    1.06
    ა
    1.05
    AN
    1.05
    לי
    1.03
    াব
    1.02
    Activations Density 0.001%

    No Known Activations