© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87243
    Prev
    Next
    INDEX
    Explanations

    estate sales, reduce, house

    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
    রোগ
    0.43
    ēng
    0.40
    宰
    0.39
     Hist
    0.38
    ++;//
    0.38
    isalpha
    0.38
     Fourier
    0.38
    Hong
    0.37
    -*
    0.37
    浈
    0.37
    POSITIVE LOGITS
    一段
    0.46
     ഏക
    0.44
     লুট
    0.41
     മൊ
    0.40
     brim
    0.40
    seh
    0.40
    akkha
    0.39
    iem
    0.39
    ական
    0.39
    iddle
    0.38
    Activations Density 0.000%

    No Known Activations