© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 151336
    Prev
    Next
    INDEX
    Explanations

    color vision differences

    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_23_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
     حقی
    0.43
     বিষ
    0.43
     depred
    0.42
    枯
    0.42
    AIR
    0.40
    codetest
    0.40
    étrique
    0.40
     फर्जी
    0.39
     जहरी
    0.39
    夺
    0.39
    POSITIVE LOGITS
     ಬಾ
    0.40
     なお
    0.39
    ண்டை
    0.39
    此之外
    0.38
    有两个
    0.36
     manca
    0.36
    णात
    0.35
     '../
    0.35
     scalability
    0.35
     macrom
    0.35
    Activations Density 0.004%

    No Known Activations