© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208953
    Prev
    Next
    INDEX
    Explanations

    comfortable seating and chairs

    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_20_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
     ablaze
    0.51
     fuoco
    0.49
    ukes
    0.49
    函数
    0.43
    ወት
    0.43
    喑
    0.42
    ৎকার
    0.42
    ziehung
    0.42
    Boy
    0.42
     ragazzo
    0.40
    POSITIVE LOGITS
    数が
    0.44
     compressed
    0.43
    compressed
    0.42
     зада
    0.41
    躯
    0.41
     dri
    0.41
    Dried
    0.41
     đa
    0.40
     footwear
    0.40
     Dried
    0.40
    Activations Density 0.001%

    No Known Activations