© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33649
    Prev
    Next
    INDEX
    Explanations

    very well, very happy, very good, very short

    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_31_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
     corresponden
    0.42
     शॉर्ट
    0.39
    )}},
    0.39
    owało
    0.39
    mış
    0.39
     criticism
    0.38
    ഘടന
    0.38
     kısa
    0.38
     alternativ
    0.38
     প্রতিনিধ
    0.38
    POSITIVE LOGITS
    後は
    0.42
     끝
    0.41
    He
    0.38
     beer
    0.38
    ∀
    0.37
    Beer
    0.37
     הם
    0.37
     dead
    0.36
     chết
    0.36
    CLUDING
    0.34
    Activations Density 0.002%

    No Known Activations