© 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. 208884
    Prev
    Next
    INDEX
    Explanations

    truly followed by appreciation or enjoyment

    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
    Ⴎ
    0.45
     genuinely
    0.44
    Salman
    0.43
    ZnO
    0.42
     Shivaji
    0.42
    本
    0.40
     remuner
    0.39
     mumkin
    0.39
    💹
    0.38
     moim
    0.38
    POSITIVE LOGITS
     உள்ள
    0.42
    cimientos
    0.41
     এখানে
    0.40
     αφού
    0.40
     кол
    0.39
     уравнение
    0.39
     другая
    0.39
     IOException
    0.38
    வான்
    0.38
    පා
    0.38
    Activations Density 0.002%

    No Known Activations