© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 51491
    Prev
    Next
    INDEX
    Explanations

    breakdown, explanation, characteristics, categories

    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
    धनों
    0.37
     aix
    0.36
     rerum
    0.35
    Uncle
    0.35
    ः
    0.35
     mutu
    0.35
     sorrow
    0.34
     vend
    0.34
     RIP
    0.34
     biochemistry
    0.34
    POSITIVE LOGITS
     खासियत
    0.39
     willow
    0.38
    主な
    0.36
    好处
    0.36
     특징
    0.35
    ]">
    0.35
     характеристики
    0.34
    Advantages
    0.33
     sylvis
    0.33
    ulai
    0.33
    Activations Density 0.046%

    No Known Activations